Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.9822. Min Act: -0.1700
Data Index: 2475709 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.9197. Min Act: -0.1700
Data Index: 1716159 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.8884. Min Act: -0.1700
Data Index: 617053 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.6072. Min Act: -0.1700
Data Index: 7831160 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.5447. Min Act: -0.1700
Data Index: 3475349 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.5447. Min Act: -0.1700
Data Index: 414334 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.5134. Min Act: -0.1700
Data Index: 217172 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.3884. Min Act: -0.1700
Data Index: 6417802 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.3884. Min Act: -0.1700
Data Index: 3080944 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.3259. Min Act: -0.1700
Data Index: 4865381 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.3572. Min Act: -0.1700
Data Index: 7916492 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.3572. Min Act: -0.1700
Data Index: 2007139 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.2947. Min Act: -0.1700
Data Index: 3048199 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.3259. Min Act: -0.1700
Data Index: 2256996 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.2947. Min Act: -0.1700
Data Index: 5198123 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.2634. Min Act: -0.1700
Data Index: 8533275 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.2634. Min Act: -0.1700
Data Index: 4209904 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.2634. Min Act: -0.1700
Data Index: 4784326 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.2322. Min Act: -0.1700
Data Index: 3770229 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9822. Min Range: -6.9822
Max Act: 6.2009. Min Act: -0.1700
Data Index: 28097 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19