Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 198 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0674. Min Range: -10.0674
Max Act: 10.0674. Min Act: -0.1700
Data Index: 2006212 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.8799. Min Act: -0.1700
Data Index: 3312767 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.8799. Min Act: -0.1700
Data Index: 3312761 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.8174. Min Act: -0.1700
Data Index: 4847427 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.7549. Min Act: -0.1700
Data Index: 1553499 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.6924. Min Act: -0.1700
Data Index: 6964565 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.6924. Min Act: -0.1700
Data Index: 88360 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.6299. Min Act: -0.1700
Data Index: 6706401 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.5049. Min Act: -0.1700
Data Index: 6914427 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.5049. Min Act: -0.1700
Data Index: 6515688 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.5049. Min Act: -0.1700
Data Index: 7667682 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.4424. Min Act: -0.1700
Data Index: 6706399 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.4424. Min Act: -0.1700
Data Index: 5745266 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.4424. Min Act: -0.1700
Data Index: 2120978 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.3799. Min Act: -0.1700
Data Index: 2367144 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.3799. Min Act: -0.1700
Data Index: 4095178 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.3799. Min Act: -0.1700
Data Index: 2840879 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.3799. Min Act: -0.1700
Data Index: 2018268 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.3799. Min Act: -0.1700
Data Index: 7183615 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0674. Min Range: -10.0674
Max Act: 9.3799. Min Act: -0.1700
Data Index: 6442594 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19