Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2891 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.5035. Min Act: -0.0001
Data Index: 1324184 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.4618. Min Act: -0.0001
Data Index: 1296971 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.2661. Min Act: -0.0001
Data Index: 222665 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.3194. Min Act: -0.0001
Data Index: 190796 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.4978. Min Act: -0.0001
Data Index: 894574 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.2931. Min Act: -0.0001
Data Index: 996067 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.2391. Min Act: -0.0001
Data Index: 812185 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.1588. Min Act: -0.0001
Data Index: 328904 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.1117. Min Act: -0.0001
Data Index: 688219 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0121. Min Act: -0.0001
Data Index: 798168 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0958. Min Act: -0.0001
Data Index: 380697 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0314. Min Act: -0.0001
Data Index: 627309 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0205. Min Act: -0.0001
Data Index: 605200 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.1059. Min Act: -0.0001
Data Index: 860218 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0816. Min Act: -0.0001
Data Index: 338769 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0529. Min Act: -0.0001
Data Index: 1297160 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.1047. Min Act: -0.0001
Data Index: 1326754 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0466. Min Act: -0.0001
Data Index: 685035 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0066. Min Act: -0.0001
Data Index: 451189 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5035. Min Range: -1.5035
Max Act: 1.0573. Min Act: -0.0001
Data Index: 36345 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19