Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.8842. Min Act: -0.1700
Data Index: 5235397 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.8842. Min Act: -0.1700
Data Index: 2820902 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.8842. Min Act: -0.1700
Data Index: 5904425 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.6967. Min Act: -0.1700
Data Index: 8018750 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.6967. Min Act: -0.1700
Data Index: 2232189 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.5717. Min Act: -0.1700
Data Index: 7147051 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.6342. Min Act: -0.1700
Data Index: 1546475 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.6342. Min Act: -0.1700
Data Index: 5210094 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.5717. Min Act: -0.1700
Data Index: 7804130 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.5092. Min Act: -0.1700
Data Index: 7061882 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.5092. Min Act: -0.1700
Data Index: 343870 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.4467. Min Act: -0.1700
Data Index: 5575182 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.4467. Min Act: -0.1700
Data Index: 3275227 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.4467. Min Act: -0.1700
Data Index: 3225693 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.3842. Min Act: -0.1700
Data Index: 7921120 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.3842. Min Act: -0.1700
Data Index: 6088800 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.3530. Min Act: -0.1700
Data Index: 4099293 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.3530. Min Act: -0.1700
Data Index: 4846842 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.3217. Min Act: -0.1698
Data Index: 5832418 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8842. Min Range: -7.8842
Max Act: 7.2905. Min Act: -0.1700
Data Index: 3503 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19