Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3838 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.6117. Min Act: -0.1700
Data Index: 8174804 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.4867. Min Act: -0.1700
Data Index: 6084583 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.4242. Min Act: -0.1700
Data Index: 5380150 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.2992. Min Act: -0.1700
Data Index: 5758243 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.2680. Min Act: -0.1700
Data Index: 8419046 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.2367. Min Act: -0.1700
Data Index: 4352912 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.2367. Min Act: -0.1700
Data Index: 2724507 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.2367. Min Act: -0.1700
Data Index: 7269214 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.1742. Min Act: -0.1700
Data Index: 3347655 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.1742. Min Act: -0.1700
Data Index: 7640281 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.1430. Min Act: -0.1700
Data Index: 2435641 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.1430. Min Act: -0.1700
Data Index: 5684432 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.1117. Min Act: -0.1700
Data Index: 5761621 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.1117. Min Act: -0.1700
Data Index: 5078684 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.0805. Min Act: -0.1700
Data Index: 7617466 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.0805. Min Act: -0.1700
Data Index: 2768488 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.0805. Min Act: -0.1700
Data Index: 5862809 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.1117. Min Act: -0.1700
Data Index: 667051 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.0492. Min Act: -0.1700
Data Index: 5809325 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6117. Min Range: -6.6117
Max Act: 6.0492. Min Act: -0.1700
Data Index: 6084297 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19