Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4675 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0432. Min Range: -6.0432
Max Act: 6.0432. Min Act: -0.1700
Data Index: 3193013 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0432. Min Range: -6.0432
Max Act: 6.0432. Min Act: -0.1700
Data Index: 7112363 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.9494. Min Act: -0.1700
Data Index: 6824458 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.9494. Min Act: -0.1700
Data Index: 294680 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8869. Min Act: -0.1700
Data Index: 8122045 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.9494. Min Act: -0.1700
Data Index: 2113891 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8869. Min Act: -0.1700
Data Index: 6708001 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8869. Min Act: -0.1700
Data Index: 7071980 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8869. Min Act: -0.1700
Data Index: 4679335 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8869. Min Act: -0.1700
Data Index: 1888359 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8869. Min Act: -0.1700
Data Index: 3068581 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8869. Min Act: -0.1700
Data Index: 8408026 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.9182. Min Act: -0.1700
Data Index: 6348400 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2127014 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8557. Min Act: -0.1700
Data Index: 3422088 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8557. Min Act: -0.1700
Data Index: 3723416 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8244. Min Act: -0.1700
Data Index: 3433692 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8244. Min Act: -0.1700
Data Index: 760698 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8244. Min Act: -0.1700
Data Index: 8268893 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0432. Min Range: -6.0432
Max Act: 5.8244. Min Act: -0.1700
Data Index: 5873018 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19