Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2018 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.8174. Min Act: -0.0001
Data Index: 1108881 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.5313. Min Act: -0.0001
Data Index: 154381 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.5029. Min Act: -0.0001
Data Index: 1120451 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.3638. Min Act: -0.0001
Data Index: 457639 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.3087. Min Act: -0.0000
Data Index: 396728 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.9032. Min Act: -0.0000
Data Index: 876312 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.2167. Min Act: -0.0001
Data Index: 969263 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.1049. Min Act: -0.0001
Data Index: 1302997 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.1046. Min Act: -0.0001
Data Index: 114772 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.1361. Min Act: -0.0001
Data Index: 1294450 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.1736. Min Act: -0.0000
Data Index: 534659 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.9426. Min Act: -0.0001
Data Index: 263086 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.0303. Min Act: -0.0001
Data Index: 64043 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.9928. Min Act: -0.0001
Data Index: 171538 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.8850. Min Act: -0.0000
Data Index: 46206 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8174. Min Range: -2.8174
Max Act: 2.0669. Min Act: -0.0001
Data Index: 430778 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.8439. Min Act: -0.0000
Data Index: 1073429 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.9733. Min Act: -0.0001
Data Index: 989462 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.9304. Min Act: -0.0000
Data Index: 402521 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8174. Min Range: -2.8174
Max Act: 1.8221. Min Act: -0.0000
Data Index: 273358 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19