Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 68 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0561. Min Range: -6.0561
Max Act: 6.0561. Min Act: -0.1700
Data Index: 1912484 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.9936. Min Act: -0.1700
Data Index: 2135171 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2384622 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.9311. Min Act: -0.1700
Data Index: 6014584 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.9311. Min Act: -0.1700
Data Index: 155976 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8999. Min Act: -0.1700
Data Index: 3787064 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 5505412 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 141626 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 5385211 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 3331298 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 198522 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 91158 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 8397743 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 127581 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8686. Min Act: -0.1700
Data Index: 1452337 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8374. Min Act: -0.1700
Data Index: 2340078 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8374. Min Act: -0.1700
Data Index: 3120318 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8374. Min Act: -0.1700
Data Index: 2540562 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8374. Min Act: -0.1700
Data Index: 1746753 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0561. Min Range: -6.0561
Max Act: 5.8374. Min Act: -0.1700
Data Index: 6425329 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19