Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.3223. Min Act: -0.1700
Data Index: 2936486 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.2598. Min Act: -0.1700
Data Index: 2026419 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.2286. Min Act: -0.1700
Data Index: 7659706 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.1973. Min Act: -0.1700
Data Index: 4562314 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.1973. Min Act: -0.1700
Data Index: 793151 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.1661. Min Act: -0.1700
Data Index: 5489742 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0723. Min Act: -0.1700
Data Index: 7871944 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0723. Min Act: -0.1700
Data Index: 504726 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0723. Min Act: -0.1700
Data Index: 6643288 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0723. Min Act: -0.1700
Data Index: 8299300 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0411. Min Act: -0.1700
Data Index: 242478 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0098. Min Act: -0.1700
Data Index: 6433046 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9786. Min Act: -0.1700
Data Index: 6884013 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9473. Min Act: -0.1700
Data Index: 54562 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9473. Min Act: -0.1700
Data Index: 22687 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9161. Min Act: -0.1700
Data Index: 5891832 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9473. Min Act: -0.1700
Data Index: 5780872 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9161. Min Act: -0.1700
Data Index: 1333571 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8848. Min Act: -0.1700
Data Index: 3304666 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8848. Min Act: -0.1700
Data Index: 2097829 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19