Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.9892. Min Act: -0.1700
Data Index: 554418 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8954. Min Act: -0.1700
Data Index: 2084635 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8642. Min Act: -0.1700
Data Index: 1964091 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8017. Min Act: -0.1700
Data Index: 7869065 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.8329. Min Act: -0.1700
Data Index: 8059521 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.7392. Min Act: -0.1700
Data Index: 2151978 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.7079. Min Act: -0.1700
Data Index: 8645707 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.7392. Min Act: -0.1700
Data Index: 5579188 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.7079. Min Act: -0.1699
Data Index: 6365764 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6767. Min Act: -0.1700
Data Index: 823233 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6454. Min Act: -0.1700
Data Index: 8604922 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6454. Min Act: -0.1700
Data Index: 2638010 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6454. Min Act: -0.1700
Data Index: 7495860 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6142. Min Act: -0.1700
Data Index: 6569274 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6142. Min Act: -0.1700
Data Index: 7692704 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6142. Min Act: -0.1700
Data Index: 72660 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.6142. Min Act: -0.1700
Data Index: 2638009 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5829. Min Act: -0.1700
Data Index: 3359480 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5829. Min Act: -0.1700
Data Index: 6982625 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9892. Min Range: -5.9892
Max Act: 5.5204. Min Act: -0.1700
Data Index: 2351593 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19