Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.9630. Min Act: -0.1700
Data Index: 7275493 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.8380. Min Act: -0.1700
Data Index: 7640429 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.7755. Min Act: -0.1700
Data Index: 2729079 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.7755. Min Act: -0.1700
Data Index: 2226004 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.7755. Min Act: -0.1700
Data Index: 6743516 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.6505. Min Act: -0.1700
Data Index: 5506348 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.6505. Min Act: -0.1700
Data Index: 7467644 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.6505. Min Act: -0.1700
Data Index: 2125047 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.6505. Min Act: -0.1700
Data Index: 2285267 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.7130. Min Act: -0.1700
Data Index: 3813140 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5255. Min Act: -0.1700
Data Index: 3821676 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.6505. Min Act: -0.1700
Data Index: 1105293 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5880. Min Act: -0.1700
Data Index: 4186060 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.6505. Min Act: -0.1700
Data Index: 2207606 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5255. Min Act: -0.1700
Data Index: 8134358 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5880. Min Act: -0.1700
Data Index: 2697505 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5255. Min Act: -0.1700
Data Index: 2426948 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5880. Min Act: -0.1700
Data Index: 7812400 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5255. Min Act: -0.1700
Data Index: 3353709 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9630. Min Range: -10.9630
Max Act: 10.5880. Min Act: -0.1700
Data Index: 3961681 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19