Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1685 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.2928. Min Act: -0.1700
Data Index: 3162518 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.3241. Min Act: -0.1700
Data Index: 5690983 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.2616. Min Act: -0.1700
Data Index: 4101699 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.2303. Min Act: -0.1700
Data Index: 4187356 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.1678. Min Act: -0.1700
Data Index: 8708196 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.1366. Min Act: -0.1700
Data Index: 6883544 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.1053. Min Act: -0.1700
Data Index: 2424800 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.0428. Min Act: -0.1700
Data Index: 6783259 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.0428. Min Act: -0.1700
Data Index: 8755053 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3241. Min Range: -5.3241
Max Act: 5.0116. Min Act: -0.1700
Data Index: 750603 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.9803. Min Act: -0.1700
Data Index: 2146855 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.9491. Min Act: -0.1700
Data Index: 2449146 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.9491. Min Act: -0.1700
Data Index: 3489975 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.8553. Min Act: -0.1700
Data Index: 1650974 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.8866. Min Act: -0.1700
Data Index: 313709 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.8866. Min Act: -0.1700
Data Index: 3610164 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.8866. Min Act: -0.1700
Data Index: 1690285 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.8866. Min Act: -0.1700
Data Index: 5155518 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.8553. Min Act: -0.1700
Data Index: 5759184 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3241. Min Range: -5.3241
Max Act: 4.8866. Min Act: -0.1700
Data Index: 8347177 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19