Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1852 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.5120. Min Act: -0.0001
Data Index: 671977 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.4484. Min Act: -0.0001
Data Index: 382670 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.4395. Min Act: -0.0001
Data Index: 1123738 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.5606. Min Act: -0.0001
Data Index: 281892 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.4924. Min Act: -0.0001
Data Index: 1157944 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.4490. Min Act: -0.0001
Data Index: 1042075 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.4422. Min Act: -0.0001
Data Index: 424172 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.4201. Min Act: -0.0001
Data Index: 667153 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.3431. Min Act: -0.0001
Data Index: 981967 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.2358. Min Act: -0.0001
Data Index: 940817 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.2110. Min Act: -0.0001
Data Index: 573243 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.0811. Min Act: -0.0001
Data Index: 505593 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.1521. Min Act: -0.0001
Data Index: 545441 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.1288. Min Act: -0.0001
Data Index: 281252 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.2717. Min Act: -0.0001
Data Index: 1299529 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.2492. Min Act: -0.0001
Data Index: 663541 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.1380. Min Act: -0.0001
Data Index: 324484 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.1244. Min Act: -0.0001
Data Index: 1260379 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.2165. Min Act: -0.0001
Data Index: 257096 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5606. Min Range: -2.5606
Max Act: 2.3495. Min Act: -0.0001
Data Index: 680836 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19