Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 350 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 5.4099. Min Range: -5.4099
Max Act: 5.4099. Min Act: -0.0001
Data Index: 1268843 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.6229. Min Act: -0.0001
Data Index: 1190766 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.6021. Min Act: -0.0001
Data Index: 1322489 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.6920. Min Act: -0.0001
Data Index: 1320555 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.6445. Min Act: -0.0001
Data Index: 290871 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.4268. Min Act: -0.0001
Data Index: 1170831 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.1728. Min Act: -0.0001
Data Index: 518316 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.2982. Min Act: -0.0001
Data Index: 330579 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4099. Min Range: -5.4099
Max Act: 3.9359. Min Act: -0.0001
Data Index: 389365 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.0855. Min Act: -0.0001
Data Index: 432378 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4099. Min Range: -5.4099
Max Act: 3.9340. Min Act: -0.0001
Data Index: 1310558 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.0614. Min Act: -0.0001
Data Index: 6068 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.3511. Min Act: -0.0001
Data Index: 21000 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4099. Min Range: -5.4099
Max Act: 3.9770. Min Act: -0.0001
Data Index: 874811 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4099. Min Range: -5.4099
Max Act: 3.9879. Min Act: -0.0001
Data Index: 1111074 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.1270. Min Act: -0.0001
Data Index: 550981 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.1154. Min Act: -0.0001
Data Index: 247597 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4099. Min Range: -5.4099
Max Act: 4.1266. Min Act: -0.0001
Data Index: 726185 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4099. Min Range: -5.4099
Max Act: 3.9336. Min Act: -0.0001
Data Index: 271768 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4099. Min Range: -5.4099
Max Act: 3.7482. Min Act: -0.0001
Data Index: 433687 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19