Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2674. Min Range: -8.2674
Max Act: 8.2674. Min Act: -0.1700
Data Index: 5741427 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2674. Min Range: -8.2674
Max Act: 8.1424. Min Act: -0.1700
Data Index: 5654128 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.6737. Min Act: -0.1700
Data Index: 4949575 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.6737. Min Act: -0.1700
Data Index: 6923427 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.6424. Min Act: -0.1700
Data Index: 439451 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.4862. Min Act: -0.1700
Data Index: 7095157 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.4862. Min Act: -0.1700
Data Index: 2951442 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.4549. Min Act: -0.1700
Data Index: 3832024 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.4237. Min Act: -0.1700
Data Index: 6073375 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.4237. Min Act: -0.1700
Data Index: 558205 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.3924. Min Act: -0.1700
Data Index: 1414803 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.3612. Min Act: -0.1700
Data Index: 1111047 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.3612. Min Act: -0.1700
Data Index: 7858621 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.2362. Min Act: -0.1700
Data Index: 4430438 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.2362. Min Act: -0.1700
Data Index: 614829 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.2049. Min Act: -0.1700
Data Index: 8389540 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.2049. Min Act: -0.1700
Data Index: 3450319 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.1737. Min Act: -0.1700
Data Index: 4378747 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.1737. Min Act: -0.1700
Data Index: 3591040 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2674. Min Range: -8.2674
Max Act: 7.2049. Min Act: -0.1700
Data Index: 3873658 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19