Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1390. Min Range: -5.1390
Max Act: 5.1390. Min Act: -0.1700
Data Index: 7827450 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.9203. Min Act: -0.1700
Data Index: 2318831 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.8265. Min Act: -0.1700
Data Index: 2507810 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7953. Min Act: -0.1700
Data Index: 4010467 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7953. Min Act: -0.1700
Data Index: 6908785 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7953. Min Act: -0.1700
Data Index: 7502810 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7640. Min Act: -0.1700
Data Index: 8251064 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7640. Min Act: -0.1700
Data Index: 4856611 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7640. Min Act: -0.1700
Data Index: 6789419 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7640. Min Act: -0.1700
Data Index: 1670961 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7328. Min Act: -0.1700
Data Index: 2728511 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7015. Min Act: -0.1700
Data Index: 879326 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7328. Min Act: -0.1700
Data Index: 432381 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7328. Min Act: -0.1700
Data Index: 1596047 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7328. Min Act: -0.1700
Data Index: 7752642 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7328. Min Act: -0.1700
Data Index: 917585 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5695321 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7015. Min Act: -0.1700
Data Index: 6059656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5756620 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1390. Min Range: -5.1390
Max Act: 4.7015. Min Act: -0.1700
Data Index: 539310 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19