Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3411 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.5399. Min Act: -0.1700
Data Index: 5304167 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.5712. Min Act: -0.1700
Data Index: 3643380 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.4462. Min Act: -0.1700
Data Index: 8670640 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.4149. Min Act: -0.1700
Data Index: 3126096 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.4149. Min Act: -0.1700
Data Index: 3696851 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.4462. Min Act: -0.1700
Data Index: 6084896 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.3837. Min Act: -0.1700
Data Index: 3708445 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.3212. Min Act: -0.1700
Data Index: 4786293 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.3212. Min Act: -0.1700
Data Index: 7819834 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.3212. Min Act: -0.1700
Data Index: 5942262 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.3212. Min Act: -0.1700
Data Index: 416775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2899. Min Act: -0.1700
Data Index: 332685 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.3212. Min Act: -0.1700
Data Index: 5424366 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2899. Min Act: -0.1700
Data Index: 4941553 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2587. Min Act: -0.1700
Data Index: 8342794 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2899. Min Act: -0.1700
Data Index: 2221448 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2274. Min Act: -0.1700
Data Index: 667629 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2587. Min Act: -0.1700
Data Index: 4551758 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2274. Min Act: -0.1700
Data Index: 6213135 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5712. Min Range: -6.5712
Max Act: 6.2274. Min Act: -0.1700
Data Index: 4860261 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19