Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4928 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0546. Min Range: -6.0546
Max Act: 6.0546. Min Act: -0.1700
Data Index: 6811680 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0546. Min Range: -6.0546
Max Act: 6.0233. Min Act: -0.1700
Data Index: 6486715 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.9608. Min Act: -0.1700
Data Index: 6490508 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.9608. Min Act: -0.1700
Data Index: 2229146 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 2042053 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.9296. Min Act: -0.1700
Data Index: 3955062 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 2587601 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.9608. Min Act: -0.1700
Data Index: 7216424 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.9296. Min Act: -0.1700
Data Index: 6261424 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 2251183 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 6400224 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 7928421 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 3508352 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 1736976 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8983. Min Act: -0.1700
Data Index: 150504 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8671. Min Act: -0.1700
Data Index: 6595160 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8671. Min Act: -0.1700
Data Index: 1507171 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8671. Min Act: -0.1700
Data Index: 5352197 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8671. Min Act: -0.1700
Data Index: 3227604 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0546. Min Range: -6.0546
Max Act: 5.8671. Min Act: -0.1700
Data Index: 4221002 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19