Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1712 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1667. Min Range: -8.1667
Max Act: 8.1667. Min Act: -0.1700
Data Index: 2979473 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.8855. Min Act: -0.1700
Data Index: 5171455 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.8542. Min Act: -0.1700
Data Index: 2298338 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.7292. Min Act: -0.1700
Data Index: 4439413 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.6042. Min Act: -0.1700
Data Index: 8079535 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.5417. Min Act: -0.1700
Data Index: 6846038 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.5105. Min Act: -0.1700
Data Index: 8225341 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.5105. Min Act: -0.1700
Data Index: 7890969 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.4792. Min Act: -0.1700
Data Index: 5457208 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.4480. Min Act: -0.1700
Data Index: 6574507 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.4167. Min Act: -0.1700
Data Index: 1163926 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.4480. Min Act: -0.1700
Data Index: 7809558 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.3542. Min Act: -0.1700
Data Index: 4790669 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.3542. Min Act: -0.1700
Data Index: 8717449 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.3542. Min Act: -0.1700
Data Index: 7340197 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.2917. Min Act: -0.1700
Data Index: 26901 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.3230. Min Act: -0.1700
Data Index: 5915829 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.2917. Min Act: -0.1700
Data Index: 7703261 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.2292. Min Act: -0.1700
Data Index: 3678482 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1667. Min Range: -8.1667
Max Act: 7.2605. Min Act: -0.1700
Data Index: 26900 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19