Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3804. Min Range: -6.3804
Max Act: 6.3804. Min Act: -0.1700
Data Index: 2463222 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3804. Min Range: -6.3804
Max Act: 6.1929. Min Act: -0.1700
Data Index: 4329221 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3804. Min Range: -6.3804
Max Act: 6.1617. Min Act: -0.1700
Data Index: 8608386 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3804. Min Range: -6.3804
Max Act: 6.0992. Min Act: -0.1700
Data Index: 4137688 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3804. Min Range: -6.3804
Max Act: 6.0679. Min Act: -0.1700
Data Index: 4405758 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3804. Min Range: -6.3804
Max Act: 6.0054. Min Act: -0.1700
Data Index: 7755477 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.9742. Min Act: -0.1700
Data Index: 637650 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.9742. Min Act: -0.1700
Data Index: 3698152 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.9742. Min Act: -0.1700
Data Index: 3099519 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.9429. Min Act: -0.1700
Data Index: 110475 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.8804. Min Act: -0.1700
Data Index: 5249389 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.8804. Min Act: -0.1700
Data Index: 2539069 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.9117. Min Act: -0.1700
Data Index: 3091035 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.8492. Min Act: -0.1700
Data Index: 5418645 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.8492. Min Act: -0.1700
Data Index: 7902721 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.8492. Min Act: -0.1700
Data Index: 6643193 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.8179. Min Act: -0.1700
Data Index: 2710700 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.8179. Min Act: -0.1700
Data Index: 3883018 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.7554. Min Act: -0.1700
Data Index: 1254430 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3804. Min Range: -6.3804
Max Act: 5.7867. Min Act: -0.1700
Data Index: 5343096 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19