Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5883 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.8147. Min Act: -0.1700
Data Index: 4853727 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.6585. Min Act: -0.1700
Data Index: 6751313 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.6585. Min Act: -0.1700
Data Index: 7465552 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5960. Min Act: -0.1700
Data Index: 4964607 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.6272. Min Act: -0.1700
Data Index: 4902496 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5960. Min Act: -0.1700
Data Index: 4964605 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5335. Min Act: -0.1700
Data Index: 5333577 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5335. Min Act: -0.1700
Data Index: 1351242 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5335. Min Act: -0.1700
Data Index: 7270113 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5022. Min Act: -0.1700
Data Index: 5900716 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4710. Min Act: -0.1700
Data Index: 6953780 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 1815379 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 215029 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 6172146 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4085. Min Act: -0.1700
Data Index: 4543424 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4085. Min Act: -0.1700
Data Index: 1145462 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4085. Min Act: -0.1700
Data Index: 4091893 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4085. Min Act: -0.1700
Data Index: 5061738 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 4395856 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3460. Min Act: -0.1700
Data Index: 6136158 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19