Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.2049. Min Act: -0.1700
Data Index: 3831559 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0799. Min Act: -0.1700
Data Index: 4409978 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0799. Min Act: -0.1700
Data Index: 2900375 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0799. Min Act: -0.1700
Data Index: 12768 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0799. Min Act: -0.1700
Data Index: 5621826 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0799. Min Act: -0.1700
Data Index: 5448948 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0799. Min Act: -0.1700
Data Index: 3729651 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0486. Min Act: -0.1700
Data Index: 8393327 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2049. Min Range: -5.2049
Max Act: 5.0486. Min Act: -0.1700
Data Index: 7303325 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9861. Min Act: -0.1700
Data Index: 8159320 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9861. Min Act: -0.1700
Data Index: 8590509 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9861. Min Act: -0.1700
Data Index: 732670 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9549. Min Act: -0.1700
Data Index: 2131910 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9861. Min Act: -0.1700
Data Index: 6885943 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9549. Min Act: -0.1700
Data Index: 691559 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9549. Min Act: -0.1700
Data Index: 3967656 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9549. Min Act: -0.1700
Data Index: 5152958 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9549. Min Act: -0.1700
Data Index: 1410170 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9549. Min Act: -0.1700
Data Index: 8694658 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2049. Min Range: -5.2049
Max Act: 4.9549. Min Act: -0.1700
Data Index: 5070938 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19