Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0440. Min Range: -5.0440
Max Act: 5.0127. Min Act: -0.1700
Data Index: 4007288 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0440. Min Range: -5.0440
Max Act: 5.0440. Min Act: -0.1700
Data Index: 6306372 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.9815. Min Act: -0.1700
Data Index: 3557685 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.9190. Min Act: -0.1700
Data Index: 6709984 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.8877. Min Act: -0.1700
Data Index: 607159 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.8252. Min Act: -0.1700
Data Index: 1309564 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7940. Min Act: -0.1700
Data Index: 3497504 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7627. Min Act: -0.1700
Data Index: 197597 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7627. Min Act: -0.1700
Data Index: 4271472 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7627. Min Act: -0.1700
Data Index: 4674384 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7627. Min Act: -0.1700
Data Index: 203226 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7627. Min Act: -0.1700
Data Index: 8150572 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7315. Min Act: -0.1700
Data Index: 5486841 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7002. Min Act: -0.1700
Data Index: 8110244 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7002. Min Act: -0.1700
Data Index: 2496162 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6623105 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7002. Min Act: -0.1700
Data Index: 2914141 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6654545 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7002. Min Act: -0.1700
Data Index: 4385664 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0440. Min Range: -5.0440
Max Act: 4.7002. Min Act: -0.1700
Data Index: 3001503 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19