Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 148 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1329. Min Range: -1.1329
Max Act: 1.1329. Min Act: -0.1700
Data Index: 7267418 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1329. Min Range: -1.1329
Max Act: 1.0803. Min Act: -0.1700
Data Index: 5886478 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1329. Min Range: -1.1329
Max Act: 1.0629. Min Act: -0.1700
Data Index: 3161049 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1329. Min Range: -1.1329
Max Act: 1.0280. Min Act: -0.1700
Data Index: 3725814 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1329. Min Range: -1.1329
Max Act: 1.0106. Min Act: -0.1700
Data Index: 6742781 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9932. Min Act: -0.1700
Data Index: 8742001 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9932. Min Act: -0.1700
Data Index: 8741999 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9759. Min Act: -0.1700
Data Index: 4939514 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9932. Min Act: -0.1700
Data Index: 7035791 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9759. Min Act: -0.1700
Data Index: 3319031 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9759. Min Act: -0.1700
Data Index: 7014483 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9759. Min Act: -0.1700
Data Index: 40101 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9759. Min Act: -0.1700
Data Index: 5417228 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9759. Min Act: -0.1699
Data Index: 5824520 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9586. Min Act: -0.1700
Data Index: 3954134 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9414. Min Act: -0.1700
Data Index: 7880328 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9414. Min Act: -0.1700
Data Index: 3725811 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9414. Min Act: -0.1700
Data Index: 5417239 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9414. Min Act: -0.1700
Data Index: 3303942 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1329. Min Range: -1.1329
Max Act: 0.9414. Min Act: -0.1699
Data Index: 4359139 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19