Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.4431. Min Act: -0.1700
Data Index: 6221884 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.2556. Min Act: -0.1700
Data Index: 6480513 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.1618. Min Act: -0.1700
Data Index: 5741575 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.1306. Min Act: -0.1700
Data Index: 4800615 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.1306. Min Act: -0.1700
Data Index: 4441491 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.1618. Min Act: -0.1700
Data Index: 8095926 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.0681. Min Act: -0.1700
Data Index: 2323444 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.0681. Min Act: -0.1700
Data Index: 5803106 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.0056. Min Act: -0.1700
Data Index: 5104376 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.0056. Min Act: -0.1700
Data Index: 6699042 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4431. Min Range: -7.4431
Max Act: 7.0056. Min Act: -0.1700
Data Index: 2813032 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.9431. Min Act: -0.1700
Data Index: 5690325 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.8493. Min Act: -0.1700
Data Index: 3175594 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.8806. Min Act: -0.1700
Data Index: 2128481 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.8493. Min Act: -0.1700
Data Index: 1142884 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.7868. Min Act: -0.1700
Data Index: 1440233 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.8493. Min Act: -0.1700
Data Index: 3875552 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.8493. Min Act: -0.1700
Data Index: 6669043 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.7868. Min Act: -0.1700
Data Index: 3185393 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4431. Min Range: -7.4431
Max Act: 6.7868. Min Act: -0.1700
Data Index: 4800965 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19