Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.8703. Min Act: -0.1700
Data Index: 2095655 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.7140. Min Act: -0.1700
Data Index: 414776 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.3703. Min Act: -0.1700
Data Index: 1432 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.3390. Min Act: -0.1700
Data Index: 6033695 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.3390. Min Act: -0.1700
Data Index: 253060 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.3078. Min Act: -0.1700
Data Index: 4990050 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.2765. Min Act: -0.1700
Data Index: 5143992 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.2140. Min Act: -0.1700
Data Index: 1289767 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.2140. Min Act: -0.1700
Data Index: 2165043 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.1515. Min Act: -0.1700
Data Index: 913252 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.1515. Min Act: -0.1700
Data Index: 1296594 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.1515. Min Act: -0.1700
Data Index: 6791467 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.1203. Min Act: -0.1700
Data Index: 3265280 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.1203. Min Act: -0.1700
Data Index: 1111533 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.1203. Min Act: -0.1700
Data Index: 617024 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.0890. Min Act: -0.1700
Data Index: 1229393 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.0890. Min Act: -0.1700
Data Index: 2203655 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.0890. Min Act: -0.1700
Data Index: 1050128 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.0578. Min Act: -0.1700
Data Index: 6712916 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8703. Min Range: -6.8703
Max Act: 6.0578. Min Act: -0.1700
Data Index: 5226665 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19