Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1876 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3638. Min Range: -10.3638
Max Act: 10.3013. Min Act: -0.1700
Data Index: 6152586 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3638. Min Range: -10.3638
Max Act: 10.3638. Min Act: -0.1700
Data Index: 7308139 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3638. Min Range: -10.3638
Max Act: 10.1763. Min Act: -0.1700
Data Index: 5062767 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3638. Min Range: -10.3638
Max Act: 10.1138. Min Act: -0.1700
Data Index: 6547199 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.9888. Min Act: -0.1700
Data Index: 6880072 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.9888. Min Act: -0.1700
Data Index: 2460472 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.9888. Min Act: -0.1700
Data Index: 7964281 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.9263. Min Act: -0.1700
Data Index: 6319214 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8638. Min Act: -0.1700
Data Index: 3534252 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8638. Min Act: -0.1700
Data Index: 7461579 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8638. Min Act: -0.1700
Data Index: 2855644 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.9263. Min Act: -0.1700
Data Index: 140673 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8638. Min Act: -0.1700
Data Index: 7264779 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8013. Min Act: -0.1700
Data Index: 7931829 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8013. Min Act: -0.1700
Data Index: 6152585 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8013. Min Act: -0.1700
Data Index: 1686571 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.8013. Min Act: -0.1700
Data Index: 7264781 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.7388. Min Act: -0.1700
Data Index: 1653980 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.7388. Min Act: -0.1700
Data Index: 7264790 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3638. Min Range: -10.3638
Max Act: 9.7388. Min Act: -0.1700
Data Index: 7264787 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19