Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0432. Min Range: -2.0432
Max Act: 2.0432. Min Act: -0.1700
Data Index: 6420287 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0432. Min Range: -2.0432
Max Act: 2.0432. Min Act: -0.1700
Data Index: 3977746 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0432. Min Range: -2.0432
Max Act: 2.0264. Min Act: -0.1700
Data Index: 8821617 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9926. Min Act: -0.1700
Data Index: 6147245 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9926. Min Act: -0.1700
Data Index: 2982887 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9757. Min Act: -0.1700
Data Index: 1515937 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9757. Min Act: -0.1700
Data Index: 3851910 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9587. Min Act: -0.1700
Data Index: 8092724 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9587. Min Act: -0.1700
Data Index: 4308957 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9418. Min Act: -0.1700
Data Index: 7504126 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9587. Min Act: -0.1700
Data Index: 6539045 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9418. Min Act: -0.1700
Data Index: 5726923 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9418. Min Act: -0.1700
Data Index: 2555649 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9418. Min Act: -0.1700
Data Index: 6981881 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9418. Min Act: -0.1700
Data Index: 8821620 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9248. Min Act: -0.1700
Data Index: 2248328 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9248. Min Act: -0.1700
Data Index: 8735575 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9248. Min Act: -0.1700
Data Index: 673010 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9077. Min Act: -0.1700
Data Index: 4403876 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0432. Min Range: -2.0432
Max Act: 1.9248. Min Act: -0.1700
Data Index: 2614681 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19