Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0395. Min Range: -7.0395
Max Act: 7.0395. Min Act: -0.1700
Data Index: 1796891 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.9770. Min Act: -0.1700
Data Index: 3734398 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.9458. Min Act: -0.1700
Data Index: 2149049 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.6958. Min Act: -0.1700
Data Index: 5087496 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.6333. Min Act: -0.1700
Data Index: 5510298 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.6020. Min Act: -0.1700
Data Index: 8662533 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5708. Min Act: -0.1700
Data Index: 4729354 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5708. Min Act: -0.1700
Data Index: 4134349 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5708. Min Act: -0.1700
Data Index: 6164475 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5708. Min Act: -0.1700
Data Index: 7125564 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5395. Min Act: -0.1700
Data Index: 8213293 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5395. Min Act: -0.1700
Data Index: 4935810 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5395. Min Act: -0.1700
Data Index: 3123816 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5083. Min Act: -0.1700
Data Index: 1185181 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.5395. Min Act: -0.1700
Data Index: 2818973 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4770. Min Act: -0.1700
Data Index: 5718069 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4770. Min Act: -0.1700
Data Index: 5328051 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4458. Min Act: -0.1700
Data Index: 1358416 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4145. Min Act: -0.1700
Data Index: 3560852 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0395. Min Range: -7.0395
Max Act: 6.4145. Min Act: -0.1700
Data Index: 2148307 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19