Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.6285. Min Act: -0.1700
Data Index: 2667596 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.5348. Min Act: -0.1700
Data Index: 6442713 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.4410. Min Act: -0.1700
Data Index: 2646389 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.4098. Min Act: -0.1700
Data Index: 1094009 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3785. Min Act: -0.1700
Data Index: 7668170 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3785. Min Act: -0.1700
Data Index: 7422551 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3473. Min Act: -0.1700
Data Index: 3460225 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3785. Min Act: -0.1700
Data Index: 844642 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3473. Min Act: -0.1700
Data Index: 5844385 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3160. Min Act: -0.1700
Data Index: 2077690 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3160. Min Act: -0.1700
Data Index: 7311266 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.3160. Min Act: -0.1700
Data Index: 7828684 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2848. Min Act: -0.1700
Data Index: 6410113 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2848. Min Act: -0.1700
Data Index: 772532 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2535. Min Act: -0.1700
Data Index: 4875574 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2848. Min Act: -0.1700
Data Index: 4711375 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2848. Min Act: -0.1700
Data Index: 4548361 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2535. Min Act: -0.1700
Data Index: 1734834 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2848. Min Act: -0.1700
Data Index: 8648985 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6285. Min Range: -5.6285
Max Act: 5.2848. Min Act: -0.1700
Data Index: 4059503 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19