Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1694. Min Range: -13.1694
Max Act: 13.1694. Min Act: -0.1700
Data Index: 731200 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1694. Min Range: -13.1694
Max Act: 13.0444. Min Act: -0.1700
Data Index: 5618914 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1694. Min Range: -13.1694
Max Act: 13.0444. Min Act: -0.1700
Data Index: 7852974 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.9194. Min Act: -0.1700
Data Index: 4089469 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.9194. Min Act: -0.1700
Data Index: 5618913 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.8569. Min Act: -0.1700
Data Index: 6870131 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.7944. Min Act: -0.1700
Data Index: 3195792 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.8569. Min Act: -0.1700
Data Index: 4997061 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.7944. Min Act: -0.1700
Data Index: 6330741 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.7319. Min Act: -0.1700
Data Index: 719115 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.7319. Min Act: -0.1700
Data Index: 5344207 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.6694. Min Act: -0.1700
Data Index: 8678299 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.6694. Min Act: -0.1700
Data Index: 8556581 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.6069. Min Act: -0.1700
Data Index: 4873697 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.6069. Min Act: -0.1700
Data Index: 5190516 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.4194. Min Act: -0.1700
Data Index: 4999022 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.4194. Min Act: -0.1700
Data Index: 1037284 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.4194. Min Act: -0.1700
Data Index: 6473285 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.3569. Min Act: -0.1700
Data Index: 4396505 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1694. Min Range: -13.1694
Max Act: 12.4194. Min Act: -0.1700
Data Index: 8057892 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19