Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 113 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.8397. Min Act: -0.1700
Data Index: 3537055 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.8709. Min Act: -0.1700
Data Index: 6842640 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.8084. Min Act: -0.1700
Data Index: 1539466 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7459. Min Act: -0.1700
Data Index: 814667 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7459. Min Act: -0.1700
Data Index: 4274468 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7459. Min Act: -0.1700
Data Index: 7489653 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7772. Min Act: -0.1700
Data Index: 618045 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7459. Min Act: -0.1700
Data Index: 521116 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7147. Min Act: -0.1700
Data Index: 501044 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7147. Min Act: -0.1700
Data Index: 296310 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7147. Min Act: -0.1700
Data Index: 6425153 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7147. Min Act: -0.1700
Data Index: 5968583 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7459. Min Act: -0.1700
Data Index: 1027410 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 1451368 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 527214 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 3428798 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 139405 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.7147. Min Act: -0.1700
Data Index: 272258 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 3432209 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 1291308 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19