Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2830. Min Act: -0.1700
Data Index: 2286250 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.3142. Min Act: -0.1700
Data Index: 7558142 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2830. Min Act: -0.1700
Data Index: 7663044 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2205. Min Act: -0.1700
Data Index: 1976863 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2517. Min Act: -0.1700
Data Index: 6075193 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2205. Min Act: -0.1700
Data Index: 1030236 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2205. Min Act: -0.1700
Data Index: 3536193 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2205. Min Act: -0.1700
Data Index: 7153514 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2205. Min Act: -0.1700
Data Index: 8040071 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1892. Min Act: -0.1700
Data Index: 5835045 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1892. Min Act: -0.1700
Data Index: 3658121 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1892. Min Act: -0.1700
Data Index: 763104 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.2205. Min Act: -0.1700
Data Index: 6282671 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1892. Min Act: -0.1700
Data Index: 2467067 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1580. Min Act: -0.1700
Data Index: 2556782 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1580. Min Act: -0.1700
Data Index: 2620011 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1580. Min Act: -0.1700
Data Index: 4074600 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1580. Min Act: -0.1700
Data Index: 3586776 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1267. Min Act: -0.1700
Data Index: 4078656 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3142. Min Range: -7.3142
Max Act: 7.1267. Min Act: -0.1700
Data Index: 5620495 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19