Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6265 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.2324. Min Act: -0.1700
Data Index: 4770648 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.2011. Min Act: -0.1700
Data Index: 635836 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.2324. Min Act: -0.1700
Data Index: 4442707 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.2324. Min Act: -0.1700
Data Index: 2760770 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.1074. Min Act: -0.1700
Data Index: 2446084 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7648659 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7815948 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.0449. Min Act: -0.1700
Data Index: 6939738 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7704584 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2324. Min Range: -6.2324
Max Act: 6.0136. Min Act: -0.1700
Data Index: 6286807 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.9824. Min Act: -0.1700
Data Index: 6428652 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.9824. Min Act: -0.1700
Data Index: 6430704 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.9824. Min Act: -0.1700
Data Index: 3344794 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.8886. Min Act: -0.1700
Data Index: 2469165 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.8886. Min Act: -0.1700
Data Index: 4634792 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.8886. Min Act: -0.1700
Data Index: 5544361 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.8886. Min Act: -0.1700
Data Index: 7883981 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.8886. Min Act: -0.1700
Data Index: 1258708 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.8886. Min Act: -0.1700
Data Index: 6195857 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2324. Min Range: -6.2324
Max Act: 5.8574. Min Act: -0.1700
Data Index: 7474729 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19