Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4091 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2745. Min Range: -6.2745
Max Act: 6.2745. Min Act: -0.1700
Data Index: 5565949 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2745. Min Range: -6.2745
Max Act: 6.2120. Min Act: -0.1700
Data Index: 1565775 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.7745. Min Act: -0.1700
Data Index: 2559637 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.8057. Min Act: -0.1700
Data Index: 1910286 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.7432. Min Act: -0.1700
Data Index: 2806783 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.6807. Min Act: -0.1700
Data Index: 1102594 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.6495. Min Act: -0.1700
Data Index: 5821839 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.6807. Min Act: -0.1700
Data Index: 927754 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.6182. Min Act: -0.1700
Data Index: 2418931 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.5870. Min Act: -0.1700
Data Index: 2880045 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.5870. Min Act: -0.1700
Data Index: 4854234 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.5557. Min Act: -0.1700
Data Index: 8646088 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7323391 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.4932. Min Act: -0.1700
Data Index: 5788358 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.5245. Min Act: -0.1700
Data Index: 6307103 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.4307. Min Act: -0.1700
Data Index: 1678501 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.4620. Min Act: -0.1700
Data Index: 414702 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.3995. Min Act: -0.1700
Data Index: 8827694 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.4307. Min Act: -0.1700
Data Index: 5692614 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2745. Min Range: -6.2745
Max Act: 5.4307. Min Act: -0.1700
Data Index: 4536631 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19