Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1408. Min Range: -8.1408
Max Act: 8.1408. Min Act: -0.1700
Data Index: 2596685 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.9533. Min Act: -0.1700
Data Index: 8458078 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.8908. Min Act: -0.1700
Data Index: 4298320 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.5158. Min Act: -0.1700
Data Index: 7085146 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.4533. Min Act: -0.1700
Data Index: 28717 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.3908. Min Act: -0.1700
Data Index: 5139879 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.3596. Min Act: -0.1700
Data Index: 56166 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.3283. Min Act: -0.1700
Data Index: 6319417 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.2658. Min Act: -0.1700
Data Index: 4226749 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.2346. Min Act: -0.1700
Data Index: 2794328 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.2346. Min Act: -0.1700
Data Index: 755073 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.2346. Min Act: -0.1700
Data Index: 5902975 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.2033. Min Act: -0.1700
Data Index: 1117821 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.2033. Min Act: -0.1700
Data Index: 7192971 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.1721. Min Act: -0.1700
Data Index: 3794437 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.1721. Min Act: -0.1700
Data Index: 1038576 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.1408. Min Act: -0.1700
Data Index: 4114375 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.1408. Min Act: -0.1700
Data Index: 7652771 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.1096. Min Act: -0.1700
Data Index: 1563270 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1408. Min Range: -8.1408
Max Act: 7.1408. Min Act: -0.1700
Data Index: 7593239 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19