Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.9047. Min Act: -0.1700
Data Index: 59232 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.9047. Min Act: -0.1700
Data Index: 4755214 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.8421. Min Act: -0.1700
Data Index: 1809682 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.8421. Min Act: -0.1700
Data Index: 7854461 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1866691 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7796. Min Act: -0.1700
Data Index: 3274173 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7796. Min Act: -0.1700
Data Index: 3487237 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7483. Min Act: -0.1700
Data Index: 6933333 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7483. Min Act: -0.1700
Data Index: 386973 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7796. Min Act: -0.1700
Data Index: 816976 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7796. Min Act: -0.1700
Data Index: 7874784 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7483. Min Act: -0.1700
Data Index: 5640355 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7170. Min Act: -0.1700
Data Index: 3666610 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7483. Min Act: -0.1700
Data Index: 5455523 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7014. Min Act: -0.1700
Data Index: 2906034 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7014. Min Act: -0.1700
Data Index: 292956 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7014. Min Act: -0.1700
Data Index: 6145772 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.7014. Min Act: -0.1700
Data Index: 2417699 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.6857. Min Act: -0.1700
Data Index: 1763001 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9047. Min Range: -3.9047
Max Act: 3.6857. Min Act: -0.1700
Data Index: 4715320 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19