Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 267 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.8887. Min Act: -0.1700
Data Index: 7084520 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.6387. Min Act: -0.1700
Data Index: 7607041 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.6075. Min Act: -0.1700
Data Index: 4029241 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.5762. Min Act: -0.1700
Data Index: 1704556 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.4825. Min Act: -0.1700
Data Index: 3281314 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.4200. Min Act: -0.1700
Data Index: 1024616 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.3887. Min Act: -0.1700
Data Index: 285551 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.2637. Min Act: -0.1700
Data Index: 5393077 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.2637. Min Act: -0.1700
Data Index: 8097940 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.2012. Min Act: -0.1700
Data Index: 7614462 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.2012. Min Act: -0.1700
Data Index: 4654428 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.1700. Min Act: -0.1700
Data Index: 1061871 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.1700. Min Act: -0.1700
Data Index: 1996397 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.1700. Min Act: -0.1700
Data Index: 1137274 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.1700. Min Act: -0.1700
Data Index: 4385938 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.1387. Min Act: -0.1700
Data Index: 6531463 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.1387. Min Act: -0.1700
Data Index: 536968 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.1075. Min Act: -0.1700
Data Index: 2345436 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.0762. Min Act: -0.1700
Data Index: 8091095 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8887. Min Range: -6.8887
Max Act: 6.0762. Min Act: -0.1700
Data Index: 3030589 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19