Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2122 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.4922. Min Act: -0.1700
Data Index: 6728203 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.2735. Min Act: -0.1700
Data Index: 6555432 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.2735. Min Act: -0.1700
Data Index: 2091284 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.2735. Min Act: -0.1700
Data Index: 5385612 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.2110. Min Act: -0.1700
Data Index: 5856802 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.1797. Min Act: -0.1700
Data Index: 1199852 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.1797. Min Act: -0.1700
Data Index: 4352928 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.1797. Min Act: -0.1700
Data Index: 8714362 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.1797. Min Act: -0.1700
Data Index: 1957780 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.1797. Min Act: -0.1700
Data Index: 7006427 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.1485. Min Act: -0.1700
Data Index: 6120444 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0860. Min Act: -0.1700
Data Index: 4736633 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0860. Min Act: -0.1700
Data Index: 854858 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0860. Min Act: -0.1700
Data Index: 4514535 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0547. Min Act: -0.1700
Data Index: 7380975 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0547. Min Act: -0.1700
Data Index: 1033006 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0235. Min Act: -0.1700
Data Index: 4303364 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0235. Min Act: -0.1700
Data Index: 7034858 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0235. Min Act: -0.1700
Data Index: 7230977 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4922. Min Range: -5.4922
Max Act: 5.0235. Min Act: -0.1700
Data Index: 3875690 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19