Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4873 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.3744. Min Act: -0.1700
Data Index: 6154536 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.3431. Min Act: -0.1700
Data Index: 5222668 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.3431. Min Act: -0.1700
Data Index: 344845 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.2494. Min Act: -0.1700
Data Index: 960544 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.2181. Min Act: -0.1700
Data Index: 3868758 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.2181. Min Act: -0.1700
Data Index: 47130 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.2181. Min Act: -0.1700
Data Index: 6571492 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1869. Min Act: -0.1700
Data Index: 200713 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1869. Min Act: -0.1700
Data Index: 3868791 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1869. Min Act: -0.1700
Data Index: 3486646 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1556. Min Act: -0.1700
Data Index: 2994207 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1556. Min Act: -0.1700
Data Index: 7042067 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1556. Min Act: -0.1700
Data Index: 6826514 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1244. Min Act: -0.1700
Data Index: 1411041 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1556. Min Act: -0.1700
Data Index: 3864763 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.1244. Min Act: -0.1700
Data Index: 3341704 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.0931. Min Act: -0.1700
Data Index: 6803367 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.0931. Min Act: -0.1700
Data Index: 5028550 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.0306. Min Act: -0.1700
Data Index: 1492117 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3744. Min Range: -4.3744
Max Act: 4.0619. Min Act: -0.1700
Data Index: 6947800 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19