Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0380. Min Range: -6.0380
Max Act: 6.0380. Min Act: -0.1700
Data Index: 4903823 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.3193. Min Act: -0.1700
Data Index: 4126265 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7553864 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1943. Min Act: -0.1700
Data Index: 900884 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1943. Min Act: -0.1700
Data Index: 1643833 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1943. Min Act: -0.1700
Data Index: 3520843 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1630. Min Act: -0.1700
Data Index: 5904035 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1630. Min Act: -0.1700
Data Index: 120926 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1630. Min Act: -0.1700
Data Index: 4833173 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1943. Min Act: -0.1700
Data Index: 5273865 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1318. Min Act: -0.1700
Data Index: 683951 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1318. Min Act: -0.1700
Data Index: 247390 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1318. Min Act: -0.1700
Data Index: 1334893 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1318. Min Act: -0.1700
Data Index: 6452962 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1318. Min Act: -0.1700
Data Index: 6257787 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1005. Min Act: -0.1700
Data Index: 6889114 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1005. Min Act: -0.1700
Data Index: 5692078 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.1005. Min Act: -0.1700
Data Index: 6342281 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.0693. Min Act: -0.1700
Data Index: 2673338 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0380. Min Range: -6.0380
Max Act: 5.0693. Min Act: -0.1700
Data Index: 3818983 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19