Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1770 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.8084. Min Act: -0.0001
Data Index: 177699 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6975. Min Act: -0.0001
Data Index: 1117012 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.7120. Min Act: -0.0001
Data Index: 677857 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6898. Min Act: -0.0001
Data Index: 1308836 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6756. Min Act: -0.0001
Data Index: 1358463 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6617. Min Act: -0.0001
Data Index: 1227591 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6586. Min Act: -0.0001
Data Index: 1225060 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6579. Min Act: -0.0001
Data Index: 207903 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6333. Min Act: -0.0001
Data Index: 878653 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6311. Min Act: -0.0001
Data Index: 103112 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6170. Min Act: -0.0001
Data Index: 438346 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5905. Min Act: -0.0001
Data Index: 996587 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5858. Min Act: -0.0001
Data Index: 516007 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5827. Min Act: -0.0001
Data Index: 828905 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.6226. Min Act: -0.0001
Data Index: 710253 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5993. Min Act: -0.0001
Data Index: 1143535 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5517. Min Act: -0.0001
Data Index: 728654 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5519. Min Act: -0.0001
Data Index: 1230188 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5619. Min Act: -0.0001
Data Index: 747969 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8084. Min Range: -0.8084
Max Act: 0.5642. Min Act: -0.0001
Data Index: 571012 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19