Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4030 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.5606. Min Act: -0.1700
Data Index: 2213295 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.4356. Min Act: -0.1700
Data Index: 6889512 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.4356. Min Act: -0.1700
Data Index: 1704282 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.3106. Min Act: -0.1700
Data Index: 2924705 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.1856. Min Act: -0.1700
Data Index: 5404869 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.2481. Min Act: -0.1700
Data Index: 4212380 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.1856. Min Act: -0.1700
Data Index: 2279329 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.1856. Min Act: -0.1700
Data Index: 7655128 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.1856. Min Act: -0.1700
Data Index: 7233787 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.1856. Min Act: -0.1700
Data Index: 5515731 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.1231. Min Act: -0.1700
Data Index: 782643 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.1231. Min Act: -0.1700
Data Index: 278891 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.0606. Min Act: -0.1700
Data Index: 7333688 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5606. Min Range: -9.5606
Max Act: 8.9981. Min Act: -0.1700
Data Index: 374229 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5606. Min Range: -9.5606
Max Act: 8.9356. Min Act: -0.1700
Data Index: 6944341 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5606. Min Range: -9.5606
Max Act: 8.9981. Min Act: -0.1700
Data Index: 2207661 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.0606. Min Act: -0.1700
Data Index: 448607 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5606. Min Range: -9.5606
Max Act: 9.0606. Min Act: -0.1700
Data Index: 644796 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5606. Min Range: -9.5606
Max Act: 8.9981. Min Act: -0.1700
Data Index: 635289 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5606. Min Range: -9.5606
Max Act: 8.9981. Min Act: -0.1700
Data Index: 1322246 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19