Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2529 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3774. Min Act: -0.1700
Data Index: 3681317 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3774. Min Act: -0.1700
Data Index: 4838575 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3617. Min Act: -0.1700
Data Index: 137479 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3617. Min Act: -0.1700
Data Index: 318386 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3617. Min Act: -0.1700
Data Index: 4070017 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3460. Min Act: -0.1700
Data Index: 3320213 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3460. Min Act: -0.1700
Data Index: 1599780 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3460. Min Act: -0.1700
Data Index: 252195 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3460. Min Act: -0.1700
Data Index: 6660187 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3460. Min Act: -0.1700
Data Index: 1963781 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3460. Min Act: -0.1700
Data Index: 5018135 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3303. Min Act: -0.1700
Data Index: 7901731 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3303. Min Act: -0.1700
Data Index: 1192880 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3460. Min Act: -0.1700
Data Index: 3416817 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3146. Min Act: -0.1700
Data Index: 4393820 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3146. Min Act: -0.1700
Data Index: 4072190 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3146. Min Act: -0.1700
Data Index: 1871730 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3146. Min Act: -0.1700
Data Index: 3564499 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.3146. Min Act: -0.1700
Data Index: 2965874 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3774. Min Range: -3.3774
Max Act: 3.2989. Min Act: -0.1700
Data Index: 3015740 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19