Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4001 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.3858. Min Act: -0.0001
Data Index: 323177 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.2414. Min Act: -0.0001
Data Index: 149175 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1670. Min Act: -0.0001
Data Index: 987534 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.2481. Min Act: -0.0001
Data Index: 1072934 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.2626. Min Act: -0.0001
Data Index: 1026067 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1338. Min Act: -0.0001
Data Index: 1349234 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1320. Min Act: -0.0001
Data Index: 719080 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1522. Min Act: -0.0001
Data Index: 535216 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.2234. Min Act: -0.0001
Data Index: 1351431 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1101. Min Act: -0.0001
Data Index: 404740 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1573. Min Act: -0.0001
Data Index: 467645 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1138. Min Act: -0.0001
Data Index: 939542 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.0811. Min Act: -0.0001
Data Index: 1023547 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1189. Min Act: -0.0001
Data Index: 263619 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.0766. Min Act: -0.0001
Data Index: 506014 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1070. Min Act: -0.0001
Data Index: 766650 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1360. Min Act: -0.0001
Data Index: 881209 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1417. Min Act: -0.0001
Data Index: 447728 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1198. Min Act: -0.0001
Data Index: 78612 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3858. Min Range: -1.3858
Max Act: 1.1580. Min Act: -0.0001
Data Index: 631251 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19