Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2232 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.5743. Min Act: -0.1700
Data Index: 8728801 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.3555. Min Act: -0.1700
Data Index: 6787760 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.3243. Min Act: -0.1700
Data Index: 5028143 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0743. Min Act: -0.1700
Data Index: 5090716 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0743. Min Act: -0.1700
Data Index: 3987003 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.9493. Min Act: -0.1700
Data Index: 1484904 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.7305. Min Act: -0.1700
Data Index: 8793289 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6993. Min Act: -0.1700
Data Index: 2451134 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 865357 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 1855081 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6368. Min Act: -0.1700
Data Index: 2936605 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 7838187 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 1215496 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 4487553 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 1118001 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.6680. Min Act: -0.1700
Data Index: 7401870 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.5743. Min Act: -0.1700
Data Index: 7104146 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.5118. Min Act: -0.1700
Data Index: 6528385 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.5430. Min Act: -0.1700
Data Index: 1738622 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5743. Min Range: -7.5743
Max Act: 6.5118. Min Act: -0.1700
Data Index: 3409262 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19