Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1978. Min Range: -7.1978
Max Act: 7.1978. Min Act: -0.1700
Data Index: 8657574 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1978. Min Range: -7.1978
Max Act: 7.1666. Min Act: -0.1700
Data Index: 5431493 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.7916. Min Act: -0.1700
Data Index: 3042088 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.7603. Min Act: -0.1700
Data Index: 5007596 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.7603. Min Act: -0.1700
Data Index: 2144544 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.7291. Min Act: -0.1700
Data Index: 5038192 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.6978. Min Act: -0.1700
Data Index: 418142 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.6978. Min Act: -0.1700
Data Index: 4097599 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5728. Min Act: -0.1700
Data Index: 4324431 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 1974016 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 5712082 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5416. Min Act: -0.1700
Data Index: 5160158 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5103. Min Act: -0.1700
Data Index: 242179 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.5103. Min Act: -0.1700
Data Index: 836772 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4791. Min Act: -0.1700
Data Index: 8579980 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4478. Min Act: -0.1700
Data Index: 5230265 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4166. Min Act: -0.1700
Data Index: 8548774 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4166. Min Act: -0.1700
Data Index: 8662796 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.4166. Min Act: -0.1700
Data Index: 7992906 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1978. Min Range: -7.1978
Max Act: 6.3541. Min Act: -0.1700
Data Index: 6714276 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19