Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6190 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.9128. Min Act: -0.1700
Data Index: 1582428 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.8503. Min Act: -0.1700
Data Index: 907771 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.8191. Min Act: -0.1700
Data Index: 5054299 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.8191. Min Act: -0.1700
Data Index: 583738 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7566. Min Act: -0.1700
Data Index: 6934745 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7566. Min Act: -0.1700
Data Index: 5203147 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7566. Min Act: -0.1700
Data Index: 2366931 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7566. Min Act: -0.1700
Data Index: 4689342 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7253. Min Act: -0.1700
Data Index: 3046924 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7253. Min Act: -0.1700
Data Index: 7407594 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.7253. Min Act: -0.1700
Data Index: 383230 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6941. Min Act: -0.1700
Data Index: 3505047 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 8716547 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 1359809 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 7009506 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 5130030 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6628. Min Act: -0.1700
Data Index: 91004 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6316. Min Act: -0.1700
Data Index: 308592 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6316. Min Act: -0.1700
Data Index: 726366 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9128. Min Range: -4.9128
Max Act: 4.6003. Min Act: -0.1700
Data Index: 5437193 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19