Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2413 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.4488. Min Act: -0.0001
Data Index: 487157 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.3158. Min Act: -0.0001
Data Index: 1586520 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.3725. Min Act: -0.0001
Data Index: 751260 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.2721. Min Act: -0.0001
Data Index: 626377 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1561. Min Act: -0.0001
Data Index: 137040 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1103. Min Act: -0.0001
Data Index: 1102736 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.2671. Min Act: -0.0001
Data Index: 1238546 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1175. Min Act: -0.0001
Data Index: 1290509 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1125. Min Act: -0.0001
Data Index: 1004204 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1026. Min Act: -0.0001
Data Index: 533094 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1203. Min Act: -0.0001
Data Index: 1263972 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.0812. Min Act: -0.0001
Data Index: 304736 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.0318. Min Act: -0.0001
Data Index: 1348486 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1207. Min Act: -0.0001
Data Index: 90288 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.0742. Min Act: -0.0001
Data Index: 337419 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.0136. Min Act: -0.0001
Data Index: 1195527 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.1333. Min Act: -0.0001
Data Index: 1210352 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4488. Min Range: -1.4488
Max Act: 0.9426. Min Act: -0.0001
Data Index: 683633 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.0891. Min Act: -0.0001
Data Index: 311232 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4488. Min Range: -1.4488
Max Act: 1.0139. Min Act: -0.0001
Data Index: 336137 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19