Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2020 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.6465. Min Act: -0.0001
Data Index: 936262 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.4027. Min Act: -0.0001
Data Index: 1304517 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.1202. Min Act: -0.0001
Data Index: 165075 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.0963. Min Act: -0.0001
Data Index: 866686 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.0850. Min Act: -0.0001
Data Index: 770865 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.0743. Min Act: -0.0001
Data Index: 407707 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.1700. Min Act: -0.0001
Data Index: 539470 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.0564. Min Act: -0.0001
Data Index: 632492 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.0224. Min Act: -0.0001
Data Index: 744832 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.0638. Min Act: -0.0001
Data Index: 255770 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.7648. Min Act: -0.0001
Data Index: 882192 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.9125. Min Act: -0.0001
Data Index: 728541 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.6736. Min Act: -0.0001
Data Index: 594420 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.9990. Min Act: -0.0001
Data Index: 803851 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6465. Min Range: -2.6465
Max Act: 2.0662. Min Act: -0.0001
Data Index: 874946 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.8576. Min Act: -0.0001
Data Index: 183384 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.9380. Min Act: -0.0001
Data Index: 536246 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.9232. Min Act: -0.0001
Data Index: 332601 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.8887. Min Act: -0.0001
Data Index: 1117967 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6465. Min Range: -2.6465
Max Act: 1.7243. Min Act: -0.0001
Data Index: 796967 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19