Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.5517. Min Act: -0.1700
Data Index: 2268637 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.5204. Min Act: -0.1700
Data Index: 2093346 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4890. Min Act: -0.1700
Data Index: 237600 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4890. Min Act: -0.1700
Data Index: 7438832 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4734. Min Act: -0.1700
Data Index: 7027268 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.5047. Min Act: -0.1700
Data Index: 1828513 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4734. Min Act: -0.1700
Data Index: 7122458 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4420. Min Act: -0.1700
Data Index: 6425660 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4420. Min Act: -0.1700
Data Index: 422535 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4577. Min Act: -0.1700
Data Index: 60278 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4577. Min Act: -0.1700
Data Index: 7080459 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4420. Min Act: -0.1700
Data Index: 170614 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4264. Min Act: -0.1700
Data Index: 476928 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4264. Min Act: -0.1700
Data Index: 4326289 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4107. Min Act: -0.1700
Data Index: 3584351 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4264. Min Act: -0.1700
Data Index: 3876683 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4107. Min Act: -0.1700
Data Index: 1268010 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4264. Min Act: -0.1700
Data Index: 7460642 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4107. Min Act: -0.1700
Data Index: 3923939 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5517. Min Range: -3.5517
Max Act: 3.4264. Min Act: -0.1700
Data Index: 7460712 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19