Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0485. Min Range: -6.0485
Max Act: 6.0485. Min Act: -0.1700
Data Index: 1755644 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.9547. Min Act: -0.1700
Data Index: 5628141 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.8922. Min Act: -0.1700
Data Index: 7195091 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.8297. Min Act: -0.1700
Data Index: 3112299 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.8297. Min Act: -0.1700
Data Index: 4603358 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.7672. Min Act: -0.1700
Data Index: 181957 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.7672. Min Act: -0.1700
Data Index: 4916228 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.7672. Min Act: -0.1700
Data Index: 5924255 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.7047. Min Act: -0.1700
Data Index: 2016183 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.7047. Min Act: -0.1700
Data Index: 6259606 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6735. Min Act: -0.1700
Data Index: 1019686 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6735. Min Act: -0.1700
Data Index: 7023494 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6735. Min Act: -0.1700
Data Index: 140230 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6422. Min Act: -0.1700
Data Index: 153666 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6422. Min Act: -0.1700
Data Index: 5490981 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6110. Min Act: -0.1700
Data Index: 8473034 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6110. Min Act: -0.1700
Data Index: 3507683 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6110. Min Act: -0.1700
Data Index: 330981 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6110. Min Act: -0.1700
Data Index: 171419 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0485. Min Range: -6.0485
Max Act: 5.6110. Min Act: -0.1700
Data Index: 2106695 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19