Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 60 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.9698. Min Act: -0.0001
Data Index: 729824 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.8091. Min Act: -0.0001
Data Index: 1309179 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.7910. Min Act: -0.0001
Data Index: 449859 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.9003. Min Act: -0.0001
Data Index: 374524 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.7986. Min Act: -0.0001
Data Index: 1279548 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.9610. Min Act: -0.0001
Data Index: 313538 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.6408. Min Act: -0.0001
Data Index: 716246 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.7314. Min Act: -0.0001
Data Index: 935463 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.6222. Min Act: -0.0001
Data Index: 1324036 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.5326. Min Act: -0.0001
Data Index: 527728 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.6258. Min Act: -0.0001
Data Index: 581953 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.4692. Min Act: -0.0001
Data Index: 139958 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.4532. Min Act: -0.0001
Data Index: 1077704 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.3481. Min Act: -0.0001
Data Index: 18818 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.2783. Min Act: -0.0001
Data Index: 785022 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.4054. Min Act: -0.0001
Data Index: 1093436 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.3752. Min Act: -0.0001
Data Index: 148620 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.2832. Min Act: -0.0001
Data Index: 748682 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.3905. Min Act: -0.0001
Data Index: 151202 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9698. Min Range: -1.9698
Max Act: 1.4733. Min Act: -0.0001
Data Index: 1101763 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19