Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2342 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.8978. Min Act: -0.1700
Data Index: 7142608 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.8978. Min Act: -0.1700
Data Index: 61241 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.8041. Min Act: -0.1700
Data Index: 3060459 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.7416. Min Act: -0.1700
Data Index: 2034552 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.7416. Min Act: -0.1700
Data Index: 2000764 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.6166. Min Act: -0.1700
Data Index: 6259820 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.5853. Min Act: -0.1700
Data Index: 539148 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.6166. Min Act: -0.1700
Data Index: 2239554 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.5541. Min Act: -0.1700
Data Index: 3531207 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.5228. Min Act: -0.1700
Data Index: 2855266 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.4603. Min Act: -0.1700
Data Index: 3792927 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.5228. Min Act: -0.1700
Data Index: 4714299 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.4291. Min Act: -0.1700
Data Index: 3606407 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.3978. Min Act: -0.1700
Data Index: 2438986 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.4291. Min Act: -0.1700
Data Index: 1723529 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.4291. Min Act: -0.1700
Data Index: 1007276 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.3666. Min Act: -0.1700
Data Index: 1740172 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.3666. Min Act: -0.1700
Data Index: 3653842 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.3666. Min Act: -0.1700
Data Index: 4978043 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8978. Min Range: -7.8978
Max Act: 7.3353. Min Act: -0.1700
Data Index: 936966 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19