Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.5354. Min Act: -0.1700
Data Index: 3926306 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.5041. Min Act: -0.1700
Data Index: 7983466 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.4729. Min Act: -0.1700
Data Index: 1693322 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.4729. Min Act: -0.1700
Data Index: 5958923 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.2854. Min Act: -0.1700
Data Index: 3906181 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.2229. Min Act: -0.1700
Data Index: 7235199 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2298238 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2341738 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.1916. Min Act: -0.1700
Data Index: 4399431 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.1604. Min Act: -0.1700
Data Index: 6352648 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.1604. Min Act: -0.1700
Data Index: 7485908 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0666. Min Act: -0.1700
Data Index: 1629900 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0979. Min Act: -0.1700
Data Index: 6092953 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0666. Min Act: -0.1700
Data Index: 3471377 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0666. Min Act: -0.1700
Data Index: 892518 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0666. Min Act: -0.1700
Data Index: 3052514 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0354. Min Act: -0.1700
Data Index: 1576344 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0354. Min Act: -0.1700
Data Index: 404717 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0354. Min Act: -0.1700
Data Index: 3233544 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5354. Min Range: -6.5354
Max Act: 6.0354. Min Act: -0.1700
Data Index: 3165030 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19