Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.9542. Min Act: -0.1700
Data Index: 4639266 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8916. Min Act: -0.1700
Data Index: 4683742 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.8447. Min Act: -0.1700
Data Index: 4696695 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7978. Min Act: -0.1700
Data Index: 5744840 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7665. Min Act: -0.1700
Data Index: 6720935 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7196. Min Act: -0.1700
Data Index: 1714844 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7353. Min Act: -0.1700
Data Index: 460586 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.7040. Min Act: -0.1700
Data Index: 1533290 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6883. Min Act: -0.1700
Data Index: 3285894 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6727. Min Act: -0.1700
Data Index: 5023873 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6570. Min Act: -0.1700
Data Index: 4403056 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6414. Min Act: -0.1700
Data Index: 2544613 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6414. Min Act: -0.1700
Data Index: 6195021 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6258. Min Act: -0.1700
Data Index: 4861728 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6414. Min Act: -0.1700
Data Index: 7220966 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6570. Min Act: -0.1700
Data Index: 5624835 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6258. Min Act: -0.1700
Data Index: 3560265 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6258. Min Act: -0.1700
Data Index: 4128527 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6258. Min Act: -0.1700
Data Index: 449314 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9542. Min Range: -3.9542
Max Act: 3.6258. Min Act: -0.1700
Data Index: 2976344 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19