Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1097 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.6428. Min Act: -0.0001
Data Index: 1274250 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.4967. Min Act: -0.0001
Data Index: 513599 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.2601. Min Act: -0.0001
Data Index: 1053241 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.2803. Min Act: -0.0001
Data Index: 713344 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.2667. Min Act: -0.0001
Data Index: 183716 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.3159. Min Act: -0.0001
Data Index: 251485 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.0561. Min Act: -0.0001
Data Index: 507026 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.1598. Min Act: -0.0001
Data Index: 418764 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.1157. Min Act: -0.0001
Data Index: 326934 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.1063. Min Act: -0.0001
Data Index: 1349373 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.0780. Min Act: -0.0001
Data Index: 621856 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.1681. Min Act: -0.0001
Data Index: 867461 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.0558. Min Act: -0.0001
Data Index: 1017205 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6428. Min Range: -2.6428
Max Act: 1.8248. Min Act: -0.0001
Data Index: 868528 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.0501. Min Act: -0.0001
Data Index: 1291003 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.1376. Min Act: -0.0001
Data Index: 207301 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.0151. Min Act: -0.0001
Data Index: 726638 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6428. Min Range: -2.6428
Max Act: 2.0067. Min Act: -0.0001
Data Index: 1040722 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6428. Min Range: -2.6428
Max Act: 1.9954. Min Act: -0.0001
Data Index: 727991 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6428. Min Range: -2.6428
Max Act: 1.9536. Min Act: -0.0001
Data Index: 202152 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19