Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1246 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.9292. Min Act: -0.1700
Data Index: 7870041 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.9292. Min Act: -0.1700
Data Index: 1643650 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.7417. Min Act: -0.1700
Data Index: 608520 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.7104. Min Act: -0.1700
Data Index: 6377496 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.6479. Min Act: -0.1700
Data Index: 6572534 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.5542. Min Act: -0.1700
Data Index: 8199416 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.6167. Min Act: -0.1700
Data Index: 2806937 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.5854. Min Act: -0.1700
Data Index: 8036121 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.5229. Min Act: -0.1700
Data Index: 1904448 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4917. Min Act: -0.1700
Data Index: 6900489 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4917. Min Act: -0.1700
Data Index: 3006 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4917. Min Act: -0.1700
Data Index: 4700922 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4292. Min Act: -0.1700
Data Index: 7867559 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4292. Min Act: -0.1700
Data Index: 2262615 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4917. Min Act: -0.1700
Data Index: 2517957 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4292. Min Act: -0.1700
Data Index: 1764884 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.3979. Min Act: -0.1700
Data Index: 4623570 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.4292. Min Act: -0.1700
Data Index: 1965728 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.3979. Min Act: -0.1700
Data Index: 2671286 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9292. Min Range: -5.9292
Max Act: 5.3979. Min Act: -0.1700
Data Index: 7436483 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19