Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 540 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.6563. Min Act: -0.1700
Data Index: 1381744 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.6251. Min Act: -0.1700
Data Index: 6130394 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.6251. Min Act: -0.1700
Data Index: 1134489 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4376. Min Act: -0.1700
Data Index: 5082922 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4688. Min Act: -0.1700
Data Index: 2071478 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4063. Min Act: -0.1700
Data Index: 2973069 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3751. Min Act: -0.1700
Data Index: 708088 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.4063. Min Act: -0.1700
Data Index: 4788801 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3126. Min Act: -0.1700
Data Index: 605529 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3438. Min Act: -0.1700
Data Index: 4933440 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3126. Min Act: -0.1700
Data Index: 8298571 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.3126. Min Act: -0.1700
Data Index: 431922 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2813. Min Act: -0.1700
Data Index: 6985941 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2501. Min Act: -0.1700
Data Index: 1215968 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2188. Min Act: -0.1700
Data Index: 4050800 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2501. Min Act: -0.1700
Data Index: 5082923 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2188. Min Act: -0.1700
Data Index: 7856232 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2501. Min Act: -0.1700
Data Index: 433328 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.2188. Min Act: -0.1700
Data Index: 5876497 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6563. Min Range: -5.6563
Max Act: 5.1876. Min Act: -0.1700
Data Index: 6166752 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19