Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5452 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2544. Min Range: -7.2544
Max Act: 7.2544. Min Act: -0.1700
Data Index: 1967134 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2544. Min Range: -7.2544
Max Act: 7.1607. Min Act: -0.1700
Data Index: 515869 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2544. Min Range: -7.2544
Max Act: 7.1294. Min Act: -0.1700
Data Index: 1986368 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2544. Min Range: -7.2544
Max Act: 7.1607. Min Act: -0.1700
Data Index: 5694290 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2544. Min Range: -7.2544
Max Act: 7.0357. Min Act: -0.1700
Data Index: 5850645 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2544. Min Range: -7.2544
Max Act: 7.0357. Min Act: -0.1700
Data Index: 6258205 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.9419. Min Act: -0.1700
Data Index: 6888607 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.9732. Min Act: -0.1700
Data Index: 3485746 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.9107. Min Act: -0.1700
Data Index: 5623473 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8794. Min Act: -0.1700
Data Index: 7289175 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8794. Min Act: -0.1700
Data Index: 3331204 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8794. Min Act: -0.1700
Data Index: 5613509 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8794. Min Act: -0.1700
Data Index: 5476443 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7582354 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7531290 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8169. Min Act: -0.1700
Data Index: 1996218 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8169. Min Act: -0.1700
Data Index: 5814380 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.8169. Min Act: -0.1700
Data Index: 1464675 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.7857. Min Act: -0.1700
Data Index: 4779949 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2544. Min Range: -7.2544
Max Act: 6.7857. Min Act: -0.1700
Data Index: 6124182 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19