Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4945 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1286. Min Range: -8.1286
Max Act: 8.1286. Min Act: -0.1700
Data Index: 8471068 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1286. Min Range: -8.1286
Max Act: 8.0036. Min Act: -0.1700
Data Index: 5192098 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.6286. Min Act: -0.1700
Data Index: 1216602 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.5973. Min Act: -0.1700
Data Index: 3194849 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.5973. Min Act: -0.1700
Data Index: 1615880 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.5973. Min Act: -0.1700
Data Index: 4291587 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.5348. Min Act: -0.1700
Data Index: 3670717 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.5036. Min Act: -0.1700
Data Index: 81276 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.4411. Min Act: -0.1700
Data Index: 6105525 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3786. Min Act: -0.1699
Data Index: 7842210 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3786. Min Act: -0.1700
Data Index: 3486653 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3473. Min Act: -0.1700
Data Index: 1216603 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3161. Min Act: -0.1700
Data Index: 6475010 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3161. Min Act: -0.1700
Data Index: 1367958 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3161. Min Act: -0.1700
Data Index: 6475007 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3161. Min Act: -0.1700
Data Index: 6475009 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.2848. Min Act: -0.1700
Data Index: 1596059 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.2848. Min Act: -0.1700
Data Index: 5124710 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.3161. Min Act: -0.1700
Data Index: 46541 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1286. Min Range: -8.1286
Max Act: 7.2536. Min Act: -0.1700
Data Index: 7206947 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19