Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.5942. Min Act: -0.1700
Data Index: 3683621 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.4067. Min Act: -0.1700
Data Index: 7141541 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.2817. Min Act: -0.1700
Data Index: 5341749 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.1567. Min Act: -0.1700
Data Index: 2607379 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.2192. Min Act: -0.1700
Data Index: 2394597 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.1255. Min Act: -0.1700
Data Index: 4169356 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.0630. Min Act: -0.1700
Data Index: 1666256 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.0942. Min Act: -0.1700
Data Index: 2116963 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.0630. Min Act: -0.1700
Data Index: 6248775 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5942. Min Range: -8.5942
Max Act: 8.0630. Min Act: -0.1700
Data Index: 1309231 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.9692. Min Act: -0.1700
Data Index: 2395299 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.9067. Min Act: -0.1700
Data Index: 7940719 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.8755. Min Act: -0.1700
Data Index: 4867583 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.8755. Min Act: -0.1700
Data Index: 6416379 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.8442. Min Act: -0.1700
Data Index: 7424989 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.8130. Min Act: -0.1700
Data Index: 2796285 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.8130. Min Act: -0.1700
Data Index: 4721941 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.8130. Min Act: -0.1700
Data Index: 2023105 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.7817. Min Act: -0.1700
Data Index: 5231847 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5942. Min Range: -8.5942
Max Act: 7.7817. Min Act: -0.1700
Data Index: 3665540 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19