Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0054. Min Range: -6.0054
Max Act: 6.0054. Min Act: -0.1700
Data Index: 2762424 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.8491. Min Act: -0.1700
Data Index: 7211780 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.8179. Min Act: -0.1693
Data Index: 1364232 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.8804. Min Act: -0.1700
Data Index: 3675060 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7866. Min Act: -0.1700
Data Index: 3809563 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 199266 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 7217227 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 6855543 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 8028100 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7866. Min Act: -0.1700
Data Index: 5355584 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1695
Data Index: 1336572 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.8179. Min Act: -0.1700
Data Index: 3706915 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 2299215 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 7792092 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7866. Min Act: -0.1700
Data Index: 3890207 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 8089100 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7241. Min Act: -0.1700
Data Index: 6548455 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.6929. Min Act: -0.1700
Data Index: 4697683 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.6929. Min Act: -0.1700
Data Index: 5202961 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0054. Min Range: -6.0054
Max Act: 5.7554. Min Act: -0.1700
Data Index: 5286258 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19