Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1657 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.6382. Min Act: -0.1700
Data Index: 7000385 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.6382. Min Act: -0.1700
Data Index: 5486655 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.5913. Min Act: -0.1700
Data Index: 152279 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.5286. Min Act: -0.1700
Data Index: 261358 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.5286. Min Act: -0.1700
Data Index: 6066878 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.5286. Min Act: -0.1700
Data Index: 7677983 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.5286. Min Act: -0.1700
Data Index: 8084475 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4973. Min Act: -0.1700
Data Index: 6018703 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4817. Min Act: -0.1700
Data Index: 752266 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4660. Min Act: -0.1700
Data Index: 6617030 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4660. Min Act: -0.1700
Data Index: 4353572 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4503. Min Act: -0.1700
Data Index: 8361885 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4660. Min Act: -0.1700
Data Index: 3811898 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4817. Min Act: -0.1700
Data Index: 7553558 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4660. Min Act: -0.1700
Data Index: 2601579 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4347. Min Act: -0.1700
Data Index: 8528387 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4190. Min Act: -0.1700
Data Index: 3160613 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4503. Min Act: -0.1700
Data Index: 6543318 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4503. Min Act: -0.1700
Data Index: 6084175 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6382. Min Range: -3.6382
Max Act: 3.4190. Min Act: -0.1700
Data Index: 4052035 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19