Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3661 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3429. Min Range: -6.3429
Max Act: 6.3429. Min Act: -0.1700
Data Index: 7782118 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3429. Min Range: -6.3429
Max Act: 6.2804. Min Act: -0.1700
Data Index: 4366406 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3429. Min Range: -6.3429
Max Act: 6.0929. Min Act: -0.1700
Data Index: 5023180 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3429. Min Range: -6.3429
Max Act: 6.0616. Min Act: -0.1700
Data Index: 6256271 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3429. Min Range: -6.3429
Max Act: 6.0304. Min Act: -0.1700
Data Index: 726171 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.9991. Min Act: -0.1700
Data Index: 4101559 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.9679. Min Act: -0.1700
Data Index: 3458366 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.9679. Min Act: -0.1700
Data Index: 6518945 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.8116. Min Act: -0.1700
Data Index: 4228505 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.7804. Min Act: -0.1700
Data Index: 3525882 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5905687 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5307419 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.7491. Min Act: -0.1700
Data Index: 305183 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.7179. Min Act: -0.1700
Data Index: 5417609 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.6866. Min Act: -0.1700
Data Index: 5596063 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.6554. Min Act: -0.1700
Data Index: 8746604 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.6554. Min Act: -0.1700
Data Index: 8494106 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.6241. Min Act: -0.1700
Data Index: 7998778 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.6554. Min Act: -0.1700
Data Index: 3646732 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3429. Min Range: -6.3429
Max Act: 5.6554. Min Act: -0.1700
Data Index: 307508 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19