Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0302. Min Range: -3.0302
Max Act: 3.0145. Min Act: -0.1700
Data Index: 208142 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.9986. Min Act: -0.1700
Data Index: 564961 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0302. Min Range: -3.0302
Max Act: 3.0302. Min Act: -0.1651
Data Index: 208120 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.9670. Min Act: -0.1700
Data Index: 4102152 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.9354. Min Act: -0.1700
Data Index: 4187139 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.9195. Min Act: -0.1700
Data Index: 1518732 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.9195. Min Act: -0.1700
Data Index: 7875804 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.9354. Min Act: -0.1700
Data Index: 6994448 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.9037. Min Act: -0.1700
Data Index: 7859407 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8878. Min Act: -0.1700
Data Index: 6244602 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8719. Min Act: -0.1700
Data Index: 7102496 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8719. Min Act: -0.1700
Data Index: 4570161 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8878. Min Act: -0.1690
Data Index: 208170 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8561. Min Act: -0.1700
Data Index: 1718645 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8719. Min Act: -0.1700
Data Index: 3846504 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8719. Min Act: -0.1687
Data Index: 208163 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8561. Min Act: -0.1699
Data Index: 208178 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8719. Min Act: -0.1700
Data Index: 4500843 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8243. Min Act: -0.1430
Data Index: 208191 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0302. Min Range: -3.0302
Max Act: 2.8561. Min Act: -0.1700
Data Index: 3120569 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19