Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2274 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2659. Min Range: -6.2659
Max Act: 6.2659. Min Act: -0.1700
Data Index: 3590424 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2659. Min Range: -6.2659
Max Act: 6.1409. Min Act: -0.1700
Data Index: 4423126 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2659. Min Range: -6.2659
Max Act: 6.1097. Min Act: -0.1700
Data Index: 7702115 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2659. Min Range: -6.2659
Max Act: 6.0472. Min Act: -0.1700
Data Index: 5870147 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2659. Min Range: -6.2659
Max Act: 6.0159. Min Act: -0.1700
Data Index: 1834834 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.9534. Min Act: -0.1700
Data Index: 1194089 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.9222. Min Act: -0.1700
Data Index: 7061144 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.9222. Min Act: -0.1700
Data Index: 3779577 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.9222. Min Act: -0.1700
Data Index: 6289940 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.9222. Min Act: -0.1700
Data Index: 246727 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.8909. Min Act: -0.1700
Data Index: 5928378 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.8597. Min Act: -0.1700
Data Index: 2872918 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.8597. Min Act: -0.1700
Data Index: 2120843 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.7972. Min Act: -0.1700
Data Index: 4845203 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.8597. Min Act: -0.1700
Data Index: 3603653 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.8284. Min Act: -0.1700
Data Index: 1502790 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.7972. Min Act: -0.1700
Data Index: 68852 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.8597. Min Act: -0.1700
Data Index: 2407321 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.8284. Min Act: -0.1700
Data Index: 2139879 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2659. Min Range: -6.2659
Max Act: 5.7972. Min Act: -0.1700
Data Index: 1280188 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19