Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4051 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.2194. Min Range: -3.2194
Max Act: 3.2194. Min Act: -0.0001
Data Index: 721263 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.7259. Min Act: -0.0001
Data Index: 1001823 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.4456. Min Act: -0.0001
Data Index: 792915 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.4820. Min Act: -0.0001
Data Index: 385518 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.6084. Min Act: -0.0001
Data Index: 867475 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.4308. Min Act: -0.0001
Data Index: 413841 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.2886. Min Act: -0.0001
Data Index: 733408 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.2966. Min Act: -0.0001
Data Index: 445285 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.2733. Min Act: -0.0001
Data Index: 204404 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.3318. Min Act: -0.0001
Data Index: 1115033 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.4558. Min Act: -0.0001
Data Index: 728172 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.4271. Min Act: -0.0001
Data Index: 130157 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.4000. Min Act: -0.0001
Data Index: 1200046 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.2603. Min Act: -0.0001
Data Index: 889861 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.2732. Min Act: -0.0001
Data Index: 606135 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.1658. Min Act: -0.0001
Data Index: 1212964 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.1430. Min Act: -0.0001
Data Index: 940288 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.2862. Min Act: -0.0001
Data Index: 425503 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2194. Min Range: -3.2194
Max Act: 2.1746. Min Act: -0.0001
Data Index: 428881 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2194. Min Range: -3.2194
Max Act: 1.8503. Min Act: -0.0001
Data Index: 410148 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19