Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1657 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.7999. Min Act: -0.0001
Data Index: 530544 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.7482. Min Act: -0.0001
Data Index: 583900 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.5471. Min Act: -0.0001
Data Index: 200302 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.6825. Min Act: -0.0001
Data Index: 1166986 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.6484. Min Act: -0.0001
Data Index: 580516 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4014. Min Act: -0.0001
Data Index: 517246 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.5676. Min Act: -0.0001
Data Index: 403604 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4378. Min Act: -0.0001
Data Index: 368826 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4853. Min Act: -0.0001
Data Index: 295606 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4588. Min Act: -0.0001
Data Index: 624564 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.3449. Min Act: -0.0001
Data Index: 93100 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4091. Min Act: -0.0001
Data Index: 573402 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4655. Min Act: -0.0001
Data Index: 1060827 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.5032. Min Act: -0.0001
Data Index: 978572 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4075. Min Act: -0.0001
Data Index: 296240 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.5376. Min Act: -0.0001
Data Index: 558658 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.3714. Min Act: -0.0001
Data Index: 16491 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4711. Min Act: -0.0001
Data Index: 1348836 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.3496. Min Act: -0.0001
Data Index: 158563 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7999. Min Range: -1.7999
Max Act: 1.4218. Min Act: -0.0001
Data Index: 1066040 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19