Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5137 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.9866. Min Act: -0.1700
Data Index: 5786250 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0179. Min Range: -6.0179
Max Act: 6.0179. Min Act: -0.1700
Data Index: 8185239 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.9554. Min Act: -0.1700
Data Index: 7101369 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.9241. Min Act: -0.1700
Data Index: 4740837 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.9241. Min Act: -0.1700
Data Index: 7404962 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.9241. Min Act: -0.1700
Data Index: 7316310 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.9554. Min Act: -0.1700
Data Index: 830835 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.8929. Min Act: -0.1700
Data Index: 5038924 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.8929. Min Act: -0.1700
Data Index: 7367883 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.8616. Min Act: -0.1700
Data Index: 3249021 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.8304. Min Act: -0.1700
Data Index: 5681970 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.8304. Min Act: -0.1700
Data Index: 3810738 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7991. Min Act: -0.1700
Data Index: 3129408 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7991. Min Act: -0.1700
Data Index: 8782363 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7991. Min Act: -0.1700
Data Index: 838059 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7991. Min Act: -0.1700
Data Index: 7027526 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7991. Min Act: -0.1700
Data Index: 5418423 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7679. Min Act: -0.1700
Data Index: 3521115 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7366. Min Act: -0.1700
Data Index: 4615857 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0179. Min Range: -6.0179
Max Act: 5.7679. Min Act: -0.1700
Data Index: 68037 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19