Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 720 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.5041. Min Act: -0.1700
Data Index: 344342 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.3166. Min Act: -0.1700
Data Index: 7816105 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.3166. Min Act: -0.1700
Data Index: 1883684 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.2853. Min Act: -0.1700
Data Index: 7078884 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.2541. Min Act: -0.1700
Data Index: 4827877 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.2541. Min Act: -0.1700
Data Index: 4311979 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.2541. Min Act: -0.1700
Data Index: 3644310 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2144862 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1916. Min Act: -0.1700
Data Index: 8408866 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1603. Min Act: -0.1700
Data Index: 2598810 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1603. Min Act: -0.1700
Data Index: 6095875 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1603. Min Act: -0.1700
Data Index: 8669107 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1603. Min Act: -0.1700
Data Index: 7447715 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1603. Min Act: -0.1700
Data Index: 7485145 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1603. Min Act: -0.1700
Data Index: 2197163 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1291. Min Act: -0.1700
Data Index: 669388 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.1291. Min Act: -0.1700
Data Index: 3044629 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.0978. Min Act: -0.1700
Data Index: 3530609 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.0978. Min Act: -0.1700
Data Index: 1762543 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5041. Min Range: -6.5041
Max Act: 6.0978. Min Act: -0.1700
Data Index: 4335417 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19