Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.3831. Min Act: -0.1700
Data Index: 7991027 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.3518. Min Act: -0.1700
Data Index: 3110477 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.3206. Min Act: -0.1700
Data Index: 2088153 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.2581. Min Act: -0.1700
Data Index: 5754223 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.2893. Min Act: -0.1700
Data Index: 1362808 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.2581. Min Act: -0.1700
Data Index: 5150913 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.2268. Min Act: -0.1700
Data Index: 3928053 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1956. Min Act: -0.1700
Data Index: 1008564 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1956. Min Act: -0.1700
Data Index: 1175769 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1643. Min Act: -0.1700
Data Index: 6603469 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1643. Min Act: -0.1700
Data Index: 5596062 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1331. Min Act: -0.1700
Data Index: 4447926 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1643. Min Act: -0.1700
Data Index: 7925575 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1956. Min Act: -0.1700
Data Index: 3359643 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1643. Min Act: -0.1700
Data Index: 6892012 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1643. Min Act: -0.1700
Data Index: 4251914 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1331. Min Act: -0.1700
Data Index: 2083077 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1331. Min Act: -0.1700
Data Index: 782497 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1643. Min Act: -0.1700
Data Index: 261463 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3831. Min Range: -4.3831
Max Act: 4.1331. Min Act: -0.1700
Data Index: 1318777 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19