Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1954. Min Range: -6.1954
Max Act: 6.1954. Min Act: -0.1700
Data Index: 7925095 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1954. Min Range: -6.1954
Max Act: 6.0392. Min Act: -0.1700
Data Index: 7925100 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1954. Min Range: -6.1954
Max Act: 6.0079. Min Act: -0.1700
Data Index: 7925098 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8517. Min Act: -0.1700
Data Index: 7925096 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7892. Min Act: -0.1700
Data Index: 2705719 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8204. Min Act: -0.1700
Data Index: 7925099 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7579. Min Act: -0.1700
Data Index: 2832472 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7892. Min Act: -0.1700
Data Index: 2705722 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7892. Min Act: -0.1700
Data Index: 2705723 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7267. Min Act: -0.1700
Data Index: 8374927 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6954. Min Act: -0.1700
Data Index: 2705724 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6954. Min Act: -0.1700
Data Index: 2599413 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6642. Min Act: -0.1700
Data Index: 42783 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6954. Min Act: -0.1700
Data Index: 5305151 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6954. Min Act: -0.1700
Data Index: 3317858 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6642. Min Act: -0.1700
Data Index: 1605591 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6642. Min Act: -0.1700
Data Index: 3703582 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6329. Min Act: -0.1700
Data Index: 3044181 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6954. Min Act: -0.1700
Data Index: 687904 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6642. Min Act: -0.1700
Data Index: 5234741 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19