Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.2339. Min Act: -0.1700
Data Index: 174201 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.2182. Min Act: -0.1700
Data Index: 5626579 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.2182. Min Act: -0.1700
Data Index: 7293874 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.1710. Min Act: -0.1700
Data Index: 3329201 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.1710. Min Act: -0.1700
Data Index: 8103494 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.1553. Min Act: -0.1700
Data Index: 1226553 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.1553. Min Act: -0.1700
Data Index: 314828 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.1238. Min Act: -0.1700
Data Index: 4932656 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0923. Min Act: -0.1700
Data Index: 5965276 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0765. Min Act: -0.1700
Data Index: 62451 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0765. Min Act: -0.1700
Data Index: 6117214 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0449. Min Act: -0.1700
Data Index: 5814017 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0292. Min Act: -0.1700
Data Index: 6220266 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0607. Min Act: -0.1700
Data Index: 7111523 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0607. Min Act: -0.1700
Data Index: 8277880 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0449. Min Act: -0.1700
Data Index: 1363537 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0134. Min Act: -0.1700
Data Index: 2730979 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2339. Min Range: -3.2339
Max Act: 3.0134. Min Act: -0.1700
Data Index: 8209279 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2339. Min Range: -3.2339
Max Act: 2.9817. Min Act: -0.1700
Data Index: 2271443 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2339. Min Range: -3.2339
Max Act: 2.9976. Min Act: -0.1700
Data Index: 1539399 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19