Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 161 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.5506. Min Act: -0.1700
Data Index: 7171791 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.5506. Min Act: -0.1700
Data Index: 675041 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.4881. Min Act: -0.1700
Data Index: 691665 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.4881. Min Act: -0.1700
Data Index: 4194450 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.4256. Min Act: -0.1700
Data Index: 7402066 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.3943. Min Act: -0.1700
Data Index: 8009030 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.3318. Min Act: -0.1700
Data Index: 3601437 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.3318. Min Act: -0.1700
Data Index: 1875149 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.3006. Min Act: -0.1700
Data Index: 2382743 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.3006. Min Act: -0.1700
Data Index: 538502 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.3006. Min Act: -0.1700
Data Index: 3692728 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.2381. Min Act: -0.1700
Data Index: 6994166 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.1756. Min Act: -0.1700
Data Index: 4459795 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.2068. Min Act: -0.1700
Data Index: 5146415 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.1756. Min Act: -0.1700
Data Index: 4584833 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.1756. Min Act: -0.1700
Data Index: 5202191 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.1756. Min Act: -0.1700
Data Index: 3844289 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.1443. Min Act: -0.1700
Data Index: 7047380 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.1756. Min Act: -0.1700
Data Index: 1294403 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5506. Min Range: -4.5506
Max Act: 4.1756. Min Act: -0.1700
Data Index: 6539018 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19