Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 490 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.4402. Min Act: -0.1700
Data Index: 2422746 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.2215. Min Act: -0.1700
Data Index: 1139851 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.1902. Min Act: -0.1700
Data Index: 42693 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.1590. Min Act: -0.1700
Data Index: 5959223 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.1277. Min Act: -0.1686
Data Index: 5221770 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0965. Min Act: -0.1700
Data Index: 4027820 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.1277. Min Act: -0.1700
Data Index: 3561053 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.1277. Min Act: -0.1700
Data Index: 3794985 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0652. Min Act: -0.1700
Data Index: 7816340 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0340. Min Act: -0.1700
Data Index: 3740662 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0652. Min Act: -0.1700
Data Index: 3041527 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0965. Min Act: -0.1700
Data Index: 7063410 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0340. Min Act: -0.1700
Data Index: 4540432 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0652. Min Act: -0.1700
Data Index: 5936174 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0340. Min Act: -0.1699
Data Index: 4280313 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0652. Min Act: -0.1697
Data Index: 4257430 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0652. Min Act: -0.1700
Data Index: 5139079 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0027. Min Act: -0.1700
Data Index: 7174009 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0027. Min Act: -0.1700
Data Index: 1611281 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4402. Min Range: -7.4402
Max Act: 7.0027. Min Act: -0.1700
Data Index: 5742864 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19