Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 687 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.3910. Min Act: -0.1700
Data Index: 4729094 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.2035. Min Act: -0.1700
Data Index: 7172696 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.2035. Min Act: -0.1700
Data Index: 8089218 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.1723. Min Act: -0.1700
Data Index: 3693833 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.1410. Min Act: -0.1700
Data Index: 7217170 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.1098. Min Act: -0.1700
Data Index: 4821400 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.1410. Min Act: -0.1700
Data Index: 1421641 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.0785. Min Act: -0.1700
Data Index: 8042192 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.1098. Min Act: -0.1700
Data Index: 376167 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.0160. Min Act: -0.1700
Data Index: 6142464 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3910. Min Range: -7.3910
Max Act: 7.0473. Min Act: -0.1700
Data Index: 1798368 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.9848. Min Act: -0.1700
Data Index: 4529987 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.8910. Min Act: -0.1700
Data Index: 2125602 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.9223. Min Act: -0.1700
Data Index: 1793331 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.8910. Min Act: -0.1700
Data Index: 4464581 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.8910. Min Act: -0.1700
Data Index: 8078082 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.8598. Min Act: -0.1700
Data Index: 6988560 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.8598. Min Act: -0.1700
Data Index: 3332540 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.8598. Min Act: -0.1700
Data Index: 8112511 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3910. Min Range: -7.3910
Max Act: 6.8598. Min Act: -0.1700
Data Index: 2335651 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19