Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2209 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2199. Min Range: -10.2199
Max Act: 10.2199. Min Act: -0.1700
Data Index: 727901 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.9074. Min Act: -0.1700
Data Index: 3546143 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.9074. Min Act: -0.1700
Data Index: 3698121 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.8449. Min Act: -0.1700
Data Index: 8182808 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.8449. Min Act: -0.1700
Data Index: 1406755 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.7199. Min Act: -0.1700
Data Index: 3927045 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.7824. Min Act: -0.1700
Data Index: 2720354 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.7824. Min Act: -0.1700
Data Index: 2705743 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.7199. Min Act: -0.1700
Data Index: 3059060 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.7199. Min Act: -0.1700
Data Index: 7607707 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5949. Min Act: -0.1700
Data Index: 3976159 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5949. Min Act: -0.1700
Data Index: 8182804 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5949. Min Act: -0.1700
Data Index: 6408431 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5949. Min Act: -0.1700
Data Index: 7082044 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5949. Min Act: -0.1700
Data Index: 6914074 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5324. Min Act: -0.1700
Data Index: 4165389 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5324. Min Act: -0.1700
Data Index: 6620642 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5324. Min Act: -0.1700
Data Index: 2980784 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.5324. Min Act: -0.1700
Data Index: 8569918 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2199. Min Range: -10.2199
Max Act: 9.4699. Min Act: -0.1700
Data Index: 6624691 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19