Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2296. Min Range: -8.2296
Max Act: 8.2296. Min Act: -0.1700
Data Index: 1591273 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9796. Min Act: -0.1700
Data Index: 5646330 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9796. Min Act: -0.1700
Data Index: 5054179 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2296. Min Range: -8.2296
Max Act: 8.0421. Min Act: -0.1700
Data Index: 6025244 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9796. Min Act: -0.1700
Data Index: 4255287 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9171. Min Act: -0.1700
Data Index: 2285191 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9171. Min Act: -0.1700
Data Index: 2431985 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9171. Min Act: -0.1700
Data Index: 2438426 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9171. Min Act: -0.1700
Data Index: 8299220 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9796. Min Act: -0.1700
Data Index: 7579118 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9171. Min Act: -0.1700
Data Index: 4250425 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.8546. Min Act: -0.1700
Data Index: 7310160 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.8546. Min Act: -0.1700
Data Index: 3024970 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.9171. Min Act: -0.1700
Data Index: 7952037 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.8546. Min Act: -0.1700
Data Index: 5826401 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.8546. Min Act: -0.1700
Data Index: 3696078 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.7921. Min Act: -0.1700
Data Index: 5573854 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.7921. Min Act: -0.1700
Data Index: 1817921 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.7921. Min Act: -0.1700
Data Index: 6251977 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2296. Min Range: -8.2296
Max Act: 7.7921. Min Act: -0.1700
Data Index: 6858426 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19