Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.8236. Min Act: -0.1700
Data Index: 4972186 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6673. Min Act: -0.1700
Data Index: 5000148 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6986. Min Act: -0.1700
Data Index: 1811490 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6361. Min Act: -0.1700
Data Index: 5234468 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6673. Min Act: -0.1699
Data Index: 532431 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6986. Min Act: -0.1700
Data Index: 6532356 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6361. Min Act: -0.1700
Data Index: 2114134 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6361. Min Act: -0.1700
Data Index: 2506386 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6361. Min Act: -0.1700
Data Index: 3905296 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6361. Min Act: -0.1700
Data Index: 5407760 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6361. Min Act: -0.1700
Data Index: 7229190 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.5736. Min Act: -0.1700
Data Index: 4157791 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.5423. Min Act: -0.1700
Data Index: 1773368 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.5736. Min Act: -0.1700
Data Index: 8378416 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6048. Min Act: -0.1700
Data Index: 812462 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6048. Min Act: -0.1700
Data Index: 5577015 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6048. Min Act: -0.1700
Data Index: 5161319 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.6048. Min Act: -0.1700
Data Index: 4536863 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.5736. Min Act: -0.1700
Data Index: 640837 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8236. Min Range: -4.8236
Max Act: 4.5736. Min Act: -0.1700
Data Index: 2479609 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19