Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 390 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1457. Min Range: -7.1457
Max Act: 7.1457. Min Act: -0.1700
Data Index: 1699614 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1457. Min Range: -7.1457
Max Act: 7.0207. Min Act: -0.1700
Data Index: 7530391 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.9582. Min Act: -0.1700
Data Index: 319539 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.9582. Min Act: -0.1700
Data Index: 7878367 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.8332. Min Act: -0.1700
Data Index: 2864023 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.8019. Min Act: -0.1700
Data Index: 4962795 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.7394. Min Act: -0.1700
Data Index: 3589545 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.6769. Min Act: -0.1700
Data Index: 8524503 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.6769. Min Act: -0.1700
Data Index: 4719354 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.6144. Min Act: -0.1700
Data Index: 559377 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.6144. Min Act: -0.1700
Data Index: 2615241 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.6144. Min Act: -0.1700
Data Index: 559378 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.6144. Min Act: -0.1700
Data Index: 7430176 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.5519. Min Act: -0.1700
Data Index: 3324128 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.5207. Min Act: -0.1700
Data Index: 5182471 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.5519. Min Act: -0.1700
Data Index: 7733840 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.4894. Min Act: -0.1700
Data Index: 8239149 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.4894. Min Act: -0.1700
Data Index: 2635666 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.4269. Min Act: -0.1700
Data Index: 1024548 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1457. Min Range: -7.1457
Max Act: 6.4269. Min Act: -0.1700
Data Index: 3809812 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19