Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.3000. Min Act: -0.1700
Data Index: 7982272 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.2375. Min Act: -0.1700
Data Index: 5931683 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.2375. Min Act: -0.1700
Data Index: 2142516 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.1437. Min Act: -0.1700
Data Index: 1014617 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.1125. Min Act: -0.1700
Data Index: 2308195 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.1125. Min Act: -0.1700
Data Index: 3528600 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0812. Min Act: -0.1700
Data Index: 6700430 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0500. Min Act: -0.1700
Data Index: 8456776 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0500. Min Act: -0.1700
Data Index: 6886202 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0812. Min Act: -0.1700
Data Index: 4021423 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0500. Min Act: -0.1700
Data Index: 5613193 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0500. Min Act: -0.1700
Data Index: 2129919 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0500. Min Act: -0.1700
Data Index: 5987918 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0500. Min Act: -0.1700
Data Index: 1429496 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0187. Min Act: -0.1700
Data Index: 8039247 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3000. Min Range: -5.3000
Max Act: 4.9875. Min Act: -0.1700
Data Index: 3663571 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3000. Min Range: -5.3000
Max Act: 4.9875. Min Act: -0.1700
Data Index: 7025582 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3000. Min Range: -5.3000
Max Act: 5.0187. Min Act: -0.1700
Data Index: 6606309 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3000. Min Range: -5.3000
Max Act: 4.9875. Min Act: -0.1700
Data Index: 5578119 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3000. Min Range: -5.3000
Max Act: 4.9562. Min Act: -0.1700
Data Index: 3088125 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19