Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4345 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3647. Min Range: -6.3647
Max Act: 6.3647. Min Act: -0.1700
Data Index: 6183622 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3647. Min Range: -6.3647
Max Act: 6.0834. Min Act: -0.1700
Data Index: 3669028 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.9272. Min Act: -0.1700
Data Index: 2140276 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8959. Min Act: -0.1700
Data Index: 4093305 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.9272. Min Act: -0.1700
Data Index: 5985322 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.9272. Min Act: -0.1700
Data Index: 3740654 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8959. Min Act: -0.1700
Data Index: 7872119 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8647. Min Act: -0.1700
Data Index: 3339278 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8647. Min Act: -0.1700
Data Index: 6985693 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8334. Min Act: -0.1700
Data Index: 169698 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8334. Min Act: -0.1700
Data Index: 4790105 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8334. Min Act: -0.1700
Data Index: 2895508 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8022. Min Act: -0.1700
Data Index: 3411248 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8022. Min Act: -0.1700
Data Index: 8514553 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.8022. Min Act: -0.1700
Data Index: 5394728 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.7397. Min Act: -0.1700
Data Index: 3012197 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.7397. Min Act: -0.1700
Data Index: 2277414 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.7397. Min Act: -0.1700
Data Index: 2465187 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.7397. Min Act: -0.1700
Data Index: 7283172 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3647. Min Range: -6.3647
Max Act: 5.7397. Min Act: -0.1700
Data Index: 5069376 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19