Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2985 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.4216. Min Act: -0.0001
Data Index: 183674 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.3076. Min Act: -0.0001
Data Index: 206901 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.2535. Min Act: -0.0001
Data Index: 591148 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4216. Min Range: -1.4216
Max Act: 0.9120. Min Act: -0.0001
Data Index: 1053702 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4216. Min Range: -1.4216
Max Act: 0.5203. Min Act: -0.0001
Data Index: 488087 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0397. Min Act: -0.0001
Data Index: 670571 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0556. Min Act: -0.0001
Data Index: 1279546 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.1449. Min Act: -0.0001
Data Index: 778959 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0528. Min Act: -0.0001
Data Index: 358093 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4216. Min Range: -1.4216
Max Act: 0.7731. Min Act: -0.0001
Data Index: 850720 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.1145. Min Act: -0.0001
Data Index: 194270 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0558. Min Act: -0.0001
Data Index: 1156099 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0375. Min Act: -0.0001
Data Index: 1341416 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0179. Min Act: -0.0001
Data Index: 1264956 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0704. Min Act: -0.0001
Data Index: 156435 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4216. Min Range: -1.4216
Max Act: 0.9510. Min Act: -0.0001
Data Index: 159230 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4216. Min Range: -1.4216
Max Act: 0.9848. Min Act: -0.0001
Data Index: 720238 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0077. Min Act: -0.0001
Data Index: 313220 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0941. Min Act: -0.0001
Data Index: 1044970 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4216. Min Range: -1.4216
Max Act: 1.0266. Min Act: -0.0001
Data Index: 1198922 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19