Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0511. Min Range: -6.0511
Max Act: 6.0511. Min Act: -0.1700
Data Index: 1410465 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8323. Min Act: -0.1700
Data Index: 3368894 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7386. Min Act: -0.1700
Data Index: 3422393 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7073. Min Act: -0.1700
Data Index: 2279680 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6761. Min Act: -0.1700
Data Index: 7927780 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6761. Min Act: -0.1700
Data Index: 7343279 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 2276294 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 3549358 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 2247902 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 2004593 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.5823. Min Act: -0.1700
Data Index: 8558826 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.5823. Min Act: -0.1700
Data Index: 2364664 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.5198. Min Act: -0.1700
Data Index: 3102304 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.5198. Min Act: -0.1700
Data Index: 7313873 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.5198. Min Act: -0.1700
Data Index: 599114 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.4886. Min Act: -0.1700
Data Index: 5202156 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.4573. Min Act: -0.1700
Data Index: 4050359 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.4573. Min Act: -0.1700
Data Index: 4488246 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.4573. Min Act: -0.1700
Data Index: 6476416 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.3948. Min Act: -0.1700
Data Index: 6614835 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19