Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4305 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.7215. Min Act: -0.1700
Data Index: 3797291 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1590. Min Act: -0.1700
Data Index: 4848917 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.1277. Min Act: -0.1700
Data Index: 6841738 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.0652. Min Act: -0.1700
Data Index: 5873736 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7215. Min Range: -7.7215
Max Act: 7.0652. Min Act: -0.1700
Data Index: 2760873 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.9715. Min Act: -0.1700
Data Index: 8266934 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.9715. Min Act: -0.1700
Data Index: 6712728 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.8777. Min Act: -0.1700
Data Index: 2130623 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.8152. Min Act: -0.1700
Data Index: 6350742 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7840. Min Act: -0.1700
Data Index: 1619924 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7527. Min Act: -0.1700
Data Index: 7026929 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.8152. Min Act: -0.1700
Data Index: 1685209 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7840. Min Act: -0.1700
Data Index: 1696277 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7215. Min Act: -0.1700
Data Index: 6617456 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7215. Min Act: -0.1700
Data Index: 5175315 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7215. Min Act: -0.1700
Data Index: 820932 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7215. Min Act: -0.1700
Data Index: 4020240 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7215. Min Act: -0.1700
Data Index: 7640020 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.7215. Min Act: -0.1700
Data Index: 7891833 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7215. Min Range: -7.7215
Max Act: 6.6902. Min Act: -0.1700
Data Index: 6950793 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19