Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3372 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 8.3199. Min Range: -8.3199
Max Act: 8.3199. Min Act: -0.0001
Data Index: 418577 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3199. Min Range: -8.3199
Max Act: 8.1423. Min Act: -0.0001
Data Index: 163740 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3199. Min Range: -8.3199
Max Act: 7.4174. Min Act: -0.0001
Data Index: 1353281 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3199. Min Range: -8.3199
Max Act: 7.4700. Min Act: -0.0001
Data Index: 465243 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3199. Min Range: -8.3199
Max Act: 7.9978. Min Act: -0.0001
Data Index: 117454 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3199. Min Range: -8.3199
Max Act: 7.4775. Min Act: -0.0001
Data Index: 347120 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.6610. Min Act: -0.0001
Data Index: 1086177 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3199. Min Range: -8.3199
Max Act: 7.1362. Min Act: -0.0001
Data Index: 1296018 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3199. Min Range: -8.3199
Max Act: 7.0103. Min Act: -0.0001
Data Index: 555766 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.9846. Min Act: -0.0001
Data Index: 815887 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.6031. Min Act: -0.0001
Data Index: 240495 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.9317. Min Act: -0.0001
Data Index: 412847 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.6675. Min Act: -0.0001
Data Index: 390526 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.1727. Min Act: -0.0001
Data Index: 1220681 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.5343. Min Act: -0.0001
Data Index: 1347578 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.3183. Min Act: -0.0001
Data Index: 589323 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.2971. Min Act: -0.0001
Data Index: 492068 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.4333. Min Act: -0.0001
Data Index: 590419 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.1947. Min Act: -0.0001
Data Index: 823639 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3199. Min Range: -8.3199
Max Act: 6.0054. Min Act: -0.0001
Data Index: 175067 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19