Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.3916. Min Act: -0.1700
Data Index: 3940645 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.2978. Min Act: -0.1700
Data Index: 7718228 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.2353. Min Act: -0.1700
Data Index: 618803 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.2353. Min Act: -0.1700
Data Index: 5725434 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.2353. Min Act: -0.1700
Data Index: 3736397 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.2041. Min Act: -0.1700
Data Index: 2081287 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.2041. Min Act: -0.1700
Data Index: 4620686 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.2041. Min Act: -0.1700
Data Index: 6312043 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1728. Min Act: -0.1700
Data Index: 7626475 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1416. Min Act: -0.1700
Data Index: 6304733 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1728. Min Act: -0.1700
Data Index: 3399912 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1728. Min Act: -0.1700
Data Index: 3936515 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1416. Min Act: -0.1700
Data Index: 1812489 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1416. Min Act: -0.1700
Data Index: 6920102 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1416. Min Act: -0.1700
Data Index: 5131779 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1416. Min Act: -0.1700
Data Index: 2581026 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1103. Min Act: -0.1700
Data Index: 6054615 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1103. Min Act: -0.1700
Data Index: 7202056 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1103. Min Act: -0.1700
Data Index: 6821696 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3916. Min Range: -6.3916
Max Act: 6.1103. Min Act: -0.1700
Data Index: 5427291 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19