Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.2256. Min Act: -0.1700
Data Index: 6330037 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.1318. Min Act: -0.1700
Data Index: 4104013 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.0380. Min Act: -0.1700
Data Index: 2125006 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2256. Min Range: -4.2256
Max Act: 4.0068. Min Act: -0.1700
Data Index: 6394076 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9443. Min Act: -0.1700
Data Index: 6960446 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9443. Min Act: -0.1700
Data Index: 5382868 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9443. Min Act: -0.1700
Data Index: 5410290 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9443. Min Act: -0.1700
Data Index: 6967283 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9130. Min Act: -0.1700
Data Index: 5368194 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9130. Min Act: -0.1700
Data Index: 1278037 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.9130. Min Act: -0.1700
Data Index: 972455 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8817. Min Act: -0.1700
Data Index: 6292180 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8817. Min Act: -0.1700
Data Index: 1055972 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8817. Min Act: -0.1700
Data Index: 7718914 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8817. Min Act: -0.1700
Data Index: 1388408 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8817. Min Act: -0.1700
Data Index: 3123127 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8348. Min Act: -0.1700
Data Index: 1964010 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8505. Min Act: -0.1700
Data Index: 3871268 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8505. Min Act: -0.1700
Data Index: 5741340 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2256. Min Range: -4.2256
Max Act: 3.8505. Min Act: -0.1700
Data Index: 5209634 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19