Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1452 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.6317. Min Act: -0.1700
Data Index: 22743 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.6005. Min Act: -0.1700
Data Index: 1803054 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.5067. Min Act: -0.1700
Data Index: 5801251 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.5067. Min Act: -0.1700
Data Index: 7393901 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.5067. Min Act: -0.1700
Data Index: 1474545 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4442. Min Act: -0.1700
Data Index: 875592 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4442. Min Act: -0.1700
Data Index: 5518287 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4755. Min Act: -0.1700
Data Index: 4690872 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4755. Min Act: -0.1700
Data Index: 1131624 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4442. Min Act: -0.1700
Data Index: 5572662 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4442. Min Act: -0.1700
Data Index: 569100 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 569109 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 2423227 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 4981124 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 4644379 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 2883694 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 3520508 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 1628360 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 4920128 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6317. Min Range: -5.6317
Max Act: 5.4130. Min Act: -0.1700
Data Index: 3328222 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19