Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2538 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0131. Min Range: -2.0131
Max Act: 2.0131. Min Act: -0.0001
Data Index: 1356615 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.9518. Min Act: -0.0001
Data Index: 89549 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6015. Min Act: -0.0001
Data Index: 830712 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6154. Min Act: -0.0001
Data Index: 23561 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.8009. Min Act: -0.0001
Data Index: 763070 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.7433. Min Act: -0.0001
Data Index: 231180 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.7273. Min Act: -0.0001
Data Index: 1083257 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.5991. Min Act: -0.0001
Data Index: 577440 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6545. Min Act: -0.0001
Data Index: 784191 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6209. Min Act: -0.0001
Data Index: 900107 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6903. Min Act: -0.0001
Data Index: 11201 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.5564. Min Act: -0.0001
Data Index: 549855 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6950. Min Act: -0.0001
Data Index: 1118118 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.4351. Min Act: -0.0001
Data Index: 1185156 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6269. Min Act: -0.0001
Data Index: 207813 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.7154. Min Act: -0.0001
Data Index: 951477 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6373. Min Act: -0.0001
Data Index: 1197932 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.6266. Min Act: -0.0001
Data Index: 1309866 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.5752. Min Act: -0.0001
Data Index: 124970 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0131. Min Range: -2.0131
Max Act: 1.7561. Min Act: -0.0001
Data Index: 424704 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19