Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5915 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.8524. Min Act: -0.1700
Data Index: 1169804 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.8211. Min Act: -0.1700
Data Index: 4524398 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.7586. Min Act: -0.1700
Data Index: 7485300 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.6336. Min Act: -0.1700
Data Index: 6170239 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.6336. Min Act: -0.1700
Data Index: 3644466 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.6336. Min Act: -0.1700
Data Index: 3138956 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.5399. Min Act: -0.1700
Data Index: 2888216 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.4774. Min Act: -0.1700
Data Index: 4641212 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.5086. Min Act: -0.1700
Data Index: 4359069 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.5086. Min Act: -0.1700
Data Index: 5506895 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.4774. Min Act: -0.1700
Data Index: 4988812 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.4774. Min Act: -0.1700
Data Index: 1183997 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.4461. Min Act: -0.1700
Data Index: 780555 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.4461. Min Act: -0.1700
Data Index: 6305034 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.4461. Min Act: -0.1700
Data Index: 3249753 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.4149. Min Act: -0.1700
Data Index: 3978845 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.3836. Min Act: -0.1700
Data Index: 465491 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.3836. Min Act: -0.1700
Data Index: 2022460 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.3836. Min Act: -0.1700
Data Index: 6072279 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8524. Min Range: -7.8524
Max Act: 7.3524. Min Act: -0.1700
Data Index: 7308648 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19