Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1141 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.6240. Min Act: -0.1700
Data Index: 4505115 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.6240. Min Act: -0.1700
Data Index: 4836645 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.6080. Min Act: -0.1700
Data Index: 373997 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.6080. Min Act: -0.1700
Data Index: 7313987 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5919. Min Act: -0.1700
Data Index: 8571267 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5757. Min Act: -0.1700
Data Index: 658465 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5596. Min Act: -0.1700
Data Index: 3147340 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5596. Min Act: -0.1700
Data Index: 7516872 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5435. Min Act: -0.1700
Data Index: 7171013 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5273. Min Act: -0.1700
Data Index: 6898313 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5435. Min Act: -0.1700
Data Index: 1572900 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5435. Min Act: -0.1700
Data Index: 2042411 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5435. Min Act: -0.1700
Data Index: 3695491 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5111. Min Act: -0.1700
Data Index: 4725029 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5273. Min Act: -0.1700
Data Index: 7694600 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5273. Min Act: -0.1700
Data Index: 80919 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.4949. Min Act: -0.1700
Data Index: 7344707 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5111. Min Act: -0.1700
Data Index: 6188329 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.5111. Min Act: -0.1700
Data Index: 6578912 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6240. Min Range: -2.6240
Max Act: 2.4949. Min Act: -0.1700
Data Index: 716382 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19