Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1579. Min Range: -6.1579
Max Act: 6.1579. Min Act: -0.1700
Data Index: 3195771 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1579. Min Range: -6.1579
Max Act: 6.0954. Min Act: -0.1700
Data Index: 76007 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.9704. Min Act: -0.1700
Data Index: 6168714 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.9391. Min Act: -0.1700
Data Index: 3451277 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.9079. Min Act: -0.1700
Data Index: 7948392 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.8141. Min Act: -0.1700
Data Index: 821390 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.8766. Min Act: -0.1700
Data Index: 6310114 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.8141. Min Act: -0.1700
Data Index: 8829296 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7829. Min Act: -0.1700
Data Index: 8565827 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7829. Min Act: -0.1700
Data Index: 5700344 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7516. Min Act: -0.1700
Data Index: 5553603 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7516. Min Act: -0.1700
Data Index: 2867711 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7516. Min Act: -0.1700
Data Index: 5883477 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7516. Min Act: -0.1700
Data Index: 330238 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7204. Min Act: -0.1700
Data Index: 4074579 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7516. Min Act: -0.1700
Data Index: 7711754 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.7204. Min Act: -0.1700
Data Index: 950900 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.6891. Min Act: -0.1700
Data Index: 2716694 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.6891. Min Act: -0.1700
Data Index: 5883476 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1579. Min Range: -6.1579
Max Act: 5.6579. Min Act: -0.1700
Data Index: 5347386 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19