Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5488. Min Range: -5.5488
Max Act: 5.5488. Min Act: -0.1698
Data Index: 5575731 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5488. Min Range: -5.5488
Max Act: 5.2363. Min Act: -0.1675
Data Index: 3169971 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.9863. Min Act: -0.1690
Data Index: 8758896 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.8613. Min Act: -0.1700
Data Index: 4235894 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.8301. Min Act: -0.1700
Data Index: 4302189 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.7988. Min Act: -0.1700
Data Index: 1708668 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.6738. Min Act: -0.1697
Data Index: 8804788 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.6738. Min Act: -0.1699
Data Index: 2017338 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.6426. Min Act: -0.1699
Data Index: 6268134 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.6113. Min Act: -0.1700
Data Index: 7289859 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.6113. Min Act: -0.1700
Data Index: 4129430 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.6426. Min Act: -0.1691
Data Index: 4759157 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.6113. Min Act: -0.1700
Data Index: 2254356 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.5176. Min Act: -0.1700
Data Index: 3616151 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.5176. Min Act: -0.1689
Data Index: 6862071 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.5488. Min Act: -0.1700
Data Index: 2459589 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.4550. Min Act: -0.1700
Data Index: 2591924 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.4863. Min Act: -0.1698
Data Index: 1098549 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.4863. Min Act: -0.1700
Data Index: 5299313 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5488. Min Range: -5.5488
Max Act: 4.4863. Min Act: -0.1700
Data Index: 1261518 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19