Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1805. Min Range: -5.1805
Max Act: 5.1805. Min Act: -0.1700
Data Index: 6400462 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8993. Min Act: -0.1700
Data Index: 2745006 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8993. Min Act: -0.1700
Data Index: 1684894 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8993. Min Act: -0.1700
Data Index: 2388000 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8368. Min Act: -0.1700
Data Index: 1271623 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8680. Min Act: -0.1700
Data Index: 163342 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8680. Min Act: -0.1700
Data Index: 8207346 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8368. Min Act: -0.1700
Data Index: 3640264 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8055. Min Act: -0.1700
Data Index: 5615054 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.8055. Min Act: -0.1700
Data Index: 6082033 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7430. Min Act: -0.1700
Data Index: 7088119 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7743. Min Act: -0.1700
Data Index: 5535666 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7430. Min Act: -0.1700
Data Index: 8583307 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7430. Min Act: -0.1700
Data Index: 2450982 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7430. Min Act: -0.1700
Data Index: 4719994 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7430. Min Act: -0.1700
Data Index: 549613 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7118. Min Act: -0.1700
Data Index: 7309919 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7430. Min Act: -0.1700
Data Index: 6716405 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7430. Min Act: -0.1700
Data Index: 6263366 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1805. Min Range: -5.1805
Max Act: 4.7118. Min Act: -0.1700
Data Index: 8500868 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19