Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.5292. Min Act: -0.1700
Data Index: 242423 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.3417. Min Act: -0.1700
Data Index: 3532943 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.3417. Min Act: -0.1700
Data Index: 3825360 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.3105. Min Act: -0.1700
Data Index: 6217806 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.2480. Min Act: -0.1700
Data Index: 6443962 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.2480. Min Act: -0.1700
Data Index: 6885020 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.1855. Min Act: -0.1700
Data Index: 7542886 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.1855. Min Act: -0.1700
Data Index: 2884853 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.1855. Min Act: -0.1700
Data Index: 3673990 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.1855. Min Act: -0.1700
Data Index: 6520564 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.1230. Min Act: -0.1700
Data Index: 8767669 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.1230. Min Act: -0.1700
Data Index: 5159464 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.0917. Min Act: -0.1700
Data Index: 7544166 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.0917. Min Act: -0.1700
Data Index: 8498049 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.0917. Min Act: -0.1700
Data Index: 3855959 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.0292. Min Act: -0.1700
Data Index: 4757619 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.0292. Min Act: -0.1700
Data Index: 6170434 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.0605. Min Act: -0.1700
Data Index: 1752423 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5292. Min Range: -5.5292
Max Act: 4.9980. Min Act: -0.1700
Data Index: 1314439 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5292. Min Range: -5.5292
Max Act: 5.0292. Min Act: -0.1700
Data Index: 6520074 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19