Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.6244. Min Act: -0.1700
Data Index: 8249351 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.6244. Min Act: -0.1700
Data Index: 1896112 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.5304. Min Act: -0.1700
Data Index: 4540617 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.4678. Min Act: -0.1700
Data Index: 3146997 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.4521. Min Act: -0.1700
Data Index: 5116325 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.4521. Min Act: -0.1700
Data Index: 8677660 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.4208. Min Act: -0.1700
Data Index: 5303411 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.4521. Min Act: -0.1700
Data Index: 6109739 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3894. Min Act: -0.1700
Data Index: 1134541 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.4051. Min Act: -0.1700
Data Index: 94369 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3894. Min Act: -0.1700
Data Index: 6314041 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3737. Min Act: -0.1700
Data Index: 2519955 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3894. Min Act: -0.1700
Data Index: 2964996 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3737. Min Act: -0.1700
Data Index: 7837119 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3424. Min Act: -0.1700
Data Index: 7239914 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3580. Min Act: -0.1700
Data Index: 2053534 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3580. Min Act: -0.1700
Data Index: 5580337 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3424. Min Act: -0.1700
Data Index: 3640335 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3424. Min Act: -0.1700
Data Index: 5992198 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6244. Min Range: -3.6244
Max Act: 3.3580. Min Act: -0.1700
Data Index: 6078442 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19