Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6339 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4008. Min Range: -7.4008
Max Act: 7.4008. Min Act: -0.1700
Data Index: 2464028 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4008. Min Range: -7.4008
Max Act: 7.3696. Min Act: -0.1700
Data Index: 2474710 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4008. Min Range: -7.4008
Max Act: 7.3383. Min Act: -0.1700
Data Index: 8197417 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4008. Min Range: -7.4008
Max Act: 7.1196. Min Act: -0.1700
Data Index: 5224449 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4008. Min Range: -7.4008
Max Act: 7.0571. Min Act: -0.1700
Data Index: 6854045 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4008. Min Range: -7.4008
Max Act: 7.0258. Min Act: -0.1700
Data Index: 3833335 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.9633. Min Act: -0.1700
Data Index: 1734104 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.9008. Min Act: -0.1700
Data Index: 8653713 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.9008. Min Act: -0.1700
Data Index: 816269 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.8071. Min Act: -0.1700
Data Index: 4863001 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.8383. Min Act: -0.1700
Data Index: 8439540 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.8383. Min Act: -0.1700
Data Index: 75935 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7758. Min Act: -0.1700
Data Index: 6238629 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7758. Min Act: -0.1700
Data Index: 475429 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7133. Min Act: -0.1700
Data Index: 8551067 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7446. Min Act: -0.1700
Data Index: 3466357 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7133. Min Act: -0.1700
Data Index: 7212012 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7133. Min Act: -0.1700
Data Index: 7961786 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7133. Min Act: -0.1700
Data Index: 7359585 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4008. Min Range: -7.4008
Max Act: 6.7446. Min Act: -0.1700
Data Index: 6383023 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19