Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.9974. Min Act: -0.1700
Data Index: 4705208 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.9036. Min Act: -0.1700
Data Index: 2803036 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.8411. Min Act: -0.1700
Data Index: 6915770 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.8099. Min Act: -0.1700
Data Index: 4357568 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.7786. Min Act: -0.1700
Data Index: 9710 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.7786. Min Act: -0.1700
Data Index: 8417914 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.7474. Min Act: -0.1700
Data Index: 8744330 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.6849. Min Act: -0.1700
Data Index: 4600824 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.6536. Min Act: -0.1700
Data Index: 6292875 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.6536. Min Act: -0.1700
Data Index: 3101706 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.6536. Min Act: -0.1700
Data Index: 648080 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.6224. Min Act: -0.1700
Data Index: 4290461 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.6224. Min Act: -0.1700
Data Index: 8124318 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.6224. Min Act: -0.1700
Data Index: 4856527 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.5911. Min Act: -0.1700
Data Index: 4829268 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.5911. Min Act: -0.1700
Data Index: 877411 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.5911. Min Act: -0.1700
Data Index: 8604990 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.5599. Min Act: -0.1700
Data Index: 8286303 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.5599. Min Act: -0.1700
Data Index: 2996257 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9974. Min Range: -6.9974
Max Act: 6.5599. Min Act: -0.1700
Data Index: 2990876 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19