Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4885 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0041. Min Range: -7.0041
Max Act: 7.0041. Min Act: -0.1700
Data Index: 346102 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.6604. Min Act: -0.1700
Data Index: 4367882 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.5666. Min Act: -0.1700
Data Index: 7774118 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.5666. Min Act: -0.1700
Data Index: 6518126 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.5041. Min Act: -0.1700
Data Index: 4702926 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.5041. Min Act: -0.1700
Data Index: 3446980 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.4416. Min Act: -0.1700
Data Index: 4158825 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.3791. Min Act: -0.1700
Data Index: 753452 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.3791. Min Act: -0.1700
Data Index: 6920643 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.3166. Min Act: -0.1700
Data Index: 7379552 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2854. Min Act: -0.1700
Data Index: 5687348 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2854. Min Act: -0.1700
Data Index: 8816633 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2541. Min Act: -0.1700
Data Index: 60383 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2541. Min Act: -0.1700
Data Index: 4710161 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2541. Min Act: -0.1700
Data Index: 6588408 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2229. Min Act: -0.1700
Data Index: 927514 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2229. Min Act: -0.1700
Data Index: 2211547 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2869448 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.2229. Min Act: -0.1700
Data Index: 4436358 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0041. Min Range: -7.0041
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2900070 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19