Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 79 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.5934. Min Act: -0.1700
Data Index: 888541 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.5464. Min Act: -0.1700
Data Index: 4122008 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.5307. Min Act: -0.1700
Data Index: 7256218 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.5151. Min Act: -0.1700
Data Index: 1988853 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4837. Min Act: -0.1700
Data Index: 7330316 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4681. Min Act: -0.1700
Data Index: 1661636 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4524. Min Act: -0.1700
Data Index: 1671562 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4524. Min Act: -0.1700
Data Index: 7121049 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4524. Min Act: -0.1700
Data Index: 4899086 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4367. Min Act: -0.1700
Data Index: 816827 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4211. Min Act: -0.1700
Data Index: 4649853 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4367. Min Act: -0.1700
Data Index: 1004164 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4054. Min Act: -0.1700
Data Index: 2131484 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4211. Min Act: -0.1700
Data Index: 5298488 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4054. Min Act: -0.1700
Data Index: 6911114 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.4054. Min Act: -0.1700
Data Index: 4109109 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.3740. Min Act: -0.1700
Data Index: 1350519 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.3897. Min Act: -0.1700
Data Index: 4402713 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.3897. Min Act: -0.1700
Data Index: 4701600 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5934. Min Range: -3.5934
Max Act: 3.3740. Min Act: -0.1700
Data Index: 433137 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19