Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4073 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.9642. Min Act: -0.0002
Data Index: 1070589 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0119. Min Range: -3.0119
Max Act: 3.0119. Min Act: -0.0001
Data Index: 897853 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.6093. Min Act: -0.0002
Data Index: 1195483 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.6009. Min Act: -0.0001
Data Index: 932526 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.3436. Min Act: -0.0001
Data Index: 265082 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.4009. Min Act: -0.0001
Data Index: 1158011 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.4660. Min Act: -0.0001
Data Index: 555257 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.3587. Min Act: -0.0001
Data Index: 361345 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.1955. Min Act: -0.0001
Data Index: 987700 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.2649. Min Act: -0.0001
Data Index: 393105 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.4802. Min Act: -0.0001
Data Index: 441601 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.2747. Min Act: -0.0001
Data Index: 839150 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.3260. Min Act: -0.0002
Data Index: 917725 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.1855. Min Act: -0.0001
Data Index: 664966 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.1677. Min Act: -0.0001
Data Index: 768246 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.0776. Min Act: -0.0001
Data Index: 1027095 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.2342. Min Act: -0.0001
Data Index: 862742 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.1934. Min Act: -0.0001
Data Index: 468823 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.1479. Min Act: -0.0001
Data Index: 253426 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0119. Min Range: -3.0119
Max Act: 2.2045. Min Act: -0.0001
Data Index: 612020 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19