Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4533 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.4389. Min Act: -0.1700
Data Index: 4946982 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.4077. Min Act: -0.1700
Data Index: 4424215 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.3764. Min Act: -0.1700
Data Index: 7052839 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.3139. Min Act: -0.1700
Data Index: 3064103 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.3139. Min Act: -0.1700
Data Index: 5628266 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.3139. Min Act: -0.1700
Data Index: 6553950 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.2827. Min Act: -0.1700
Data Index: 1607201 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.2202. Min Act: -0.1700
Data Index: 4461812 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1889. Min Act: -0.1700
Data Index: 5433728 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1577. Min Act: -0.1700
Data Index: 3626502 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1889. Min Act: -0.1700
Data Index: 4897333 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1577. Min Act: -0.1700
Data Index: 8549226 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1264. Min Act: -0.1700
Data Index: 3707878 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1264. Min Act: -0.1700
Data Index: 3741860 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1264. Min Act: -0.1700
Data Index: 1762885 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.1264. Min Act: -0.1700
Data Index: 1087735 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.0951. Min Act: -0.1700
Data Index: 2103249 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.0951. Min Act: -0.1700
Data Index: 1796504 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.0951. Min Act: -0.1700
Data Index: 8253944 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4389. Min Range: -4.4389
Max Act: 4.0639. Min Act: -0.1700
Data Index: 3547999 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19