Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1140 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1844. Min Act: -0.1700
Data Index: 8017723 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1512. Min Act: -0.1700
Data Index: 7785687 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1678. Min Act: -0.1700
Data Index: 7667820 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1678. Min Act: -0.1700
Data Index: 7385975 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1512. Min Act: -0.1700
Data Index: 8693176 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1345. Min Act: -0.1700
Data Index: 453348 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1345. Min Act: -0.1700
Data Index: 3633741 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1345. Min Act: -0.1700
Data Index: 7190802 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1178. Min Act: -0.1700
Data Index: 7142721 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1010. Min Act: -0.1700
Data Index: 4635664 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1010. Min Act: -0.1700
Data Index: 8229195 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1010. Min Act: -0.1700
Data Index: 660223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.0675. Min Act: -0.1700
Data Index: 2956483 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1010. Min Act: -0.1700
Data Index: 3261473 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.0843. Min Act: -0.1700
Data Index: 4524996 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1010. Min Act: -0.1700
Data Index: 5709586 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.1010. Min Act: -0.1700
Data Index: 7648499 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.0843. Min Act: -0.1700
Data Index: 623492 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.0843. Min Act: -0.1700
Data Index: 6705409 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1844. Min Range: -2.1844
Max Act: 2.0843. Min Act: -0.1700
Data Index: 6921521 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19