Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 466 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2801. Min Range: -7.2801
Max Act: 7.2801. Min Act: -0.1700
Data Index: 609991 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2801. Min Range: -7.2801
Max Act: 7.2801. Min Act: -0.1700
Data Index: 2997137 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2801. Min Range: -7.2801
Max Act: 7.2176. Min Act: -0.1700
Data Index: 5179126 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2801. Min Range: -7.2801
Max Act: 7.2176. Min Act: -0.1700
Data Index: 1099957 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2801. Min Range: -7.2801
Max Act: 7.0301. Min Act: -0.1700
Data Index: 2721140 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2801. Min Range: -7.2801
Max Act: 7.0301. Min Act: -0.1700
Data Index: 6190691 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.9363. Min Act: -0.1700
Data Index: 8609270 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.8738. Min Act: -0.1700
Data Index: 7459568 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.8738. Min Act: -0.1700
Data Index: 8257477 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.7488. Min Act: -0.1700
Data Index: 5458501 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.7176. Min Act: -0.1700
Data Index: 3472467 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.7176. Min Act: -0.1700
Data Index: 243051 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.6238. Min Act: -0.1700
Data Index: 6021677 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.6551. Min Act: -0.1700
Data Index: 2885959 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.6863. Min Act: -0.1700
Data Index: 3149201 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.5926. Min Act: -0.1700
Data Index: 4945680 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.5926. Min Act: -0.1700
Data Index: 6442564 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.5926. Min Act: -0.1700
Data Index: 170648 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.4676. Min Act: -0.1700
Data Index: 4750016 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2801. Min Range: -7.2801
Max Act: 6.5301. Min Act: -0.1700
Data Index: 386286 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19