Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.9494. Min Act: -0.1700
Data Index: 4721530 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.5431. Min Act: -0.1700
Data Index: 7271164 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.5119. Min Act: -0.1700
Data Index: 8610766 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.3869. Min Act: -0.1700
Data Index: 6328503 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.3244. Min Act: -0.1700
Data Index: 159656 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.2931. Min Act: -0.1700
Data Index: 1114983 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.2619. Min Act: -0.1700
Data Index: 2912571 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.2619. Min Act: -0.1700
Data Index: 8389309 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.2306. Min Act: -0.1700
Data Index: 3168517 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.2306. Min Act: -0.1700
Data Index: 2693454 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1994. Min Act: -0.1700
Data Index: 6365494 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1681. Min Act: -0.1700
Data Index: 2170638 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1994. Min Act: -0.1700
Data Index: 1845495 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1994. Min Act: -0.1700
Data Index: 7963060 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1994. Min Act: -0.1700
Data Index: 7319576 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1994. Min Act: -0.1700
Data Index: 3061354 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1681. Min Act: -0.1700
Data Index: 6182572 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1369. Min Act: -0.1700
Data Index: 8245089 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1369. Min Act: -0.1700
Data Index: 6671584 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9494. Min Range: -7.9494
Max Act: 7.1056. Min Act: -0.1700
Data Index: 1848859 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19