Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 614 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0357. Min Range: -6.0357
Max Act: 6.0357. Min Act: -0.1700
Data Index: 5529393 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.9420. Min Act: -0.1700
Data Index: 1096164 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.8482. Min Act: -0.1700
Data Index: 6940515 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.8482. Min Act: -0.1700
Data Index: 6802055 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.7857. Min Act: -0.1700
Data Index: 8588017 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.7545. Min Act: -0.1700
Data Index: 5392140 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.7232. Min Act: -0.1700
Data Index: 7497364 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6920. Min Act: -0.1700
Data Index: 637019 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.7232. Min Act: -0.1700
Data Index: 444446 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.7232. Min Act: -0.1700
Data Index: 4746880 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6920. Min Act: -0.1700
Data Index: 1870669 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6607. Min Act: -0.1700
Data Index: 6499066 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6607. Min Act: -0.1700
Data Index: 707583 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6607. Min Act: -0.1700
Data Index: 4796516 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6295. Min Act: -0.1700
Data Index: 7854949 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6607. Min Act: -0.1700
Data Index: 1082336 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6295. Min Act: -0.1700
Data Index: 3522487 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6295. Min Act: -0.1700
Data Index: 5623166 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6295. Min Act: -0.1700
Data Index: 642552 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0357. Min Range: -6.0357
Max Act: 5.6295. Min Act: -0.1700
Data Index: 6811473 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19