Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.7191. Min Act: -0.1700
Data Index: 5352547 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.7191. Min Act: -0.1696
Data Index: 4050507 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6879. Min Act: -0.1698
Data Index: 4050510 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6879. Min Act: -0.1700
Data Index: 4050504 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6879. Min Act: -0.1700
Data Index: 1187417 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6566. Min Act: -0.1700
Data Index: 149222 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6566. Min Act: -0.1700
Data Index: 7994573 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6566. Min Act: -0.1682
Data Index: 5301765 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6254. Min Act: -0.1700
Data Index: 6012398 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6566. Min Act: -0.1697
Data Index: 6575426 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6254. Min Act: -0.1700
Data Index: 4050515 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6254. Min Act: -0.1700
Data Index: 201007 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6254. Min Act: -0.1700
Data Index: 977738 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6254. Min Act: -0.1700
Data Index: 7032768 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.6254. Min Act: -0.1697
Data Index: 6595411 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.5941. Min Act: -0.1700
Data Index: 5796598 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.5941. Min Act: -0.1700
Data Index: 6107059 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.5941. Min Act: -0.1700
Data Index: 3438445 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.5941. Min Act: -0.1700
Data Index: 4487581 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7191. Min Range: -4.7191
Max Act: 4.5941. Min Act: -0.1700
Data Index: 1187414 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19