Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2817 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1729. Min Act: -0.0001
Data Index: 1140764 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1682. Min Act: -0.0001
Data Index: 185269 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1469. Min Act: -0.0001
Data Index: 933084 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1489. Min Act: -0.0001
Data Index: 493178 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1472. Min Act: -0.0001
Data Index: 937023 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1169. Min Act: -0.0001
Data Index: 285983 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1289. Min Act: -0.0001
Data Index: 665939 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1261. Min Act: -0.0001
Data Index: 355036 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1574. Min Act: -0.0001
Data Index: 778940 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1288. Min Act: -0.0001
Data Index: 1152900 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1206. Min Act: -0.0001
Data Index: 442624 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1283. Min Act: -0.0001
Data Index: 1372198 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1090. Min Act: -0.0001
Data Index: 20250 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1082. Min Act: -0.0001
Data Index: 401340 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1219. Min Act: -0.0001
Data Index: 1548324 (Python Code)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1164. Min Act: -0.0001
Data Index: 1330008 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1108. Min Act: -0.0001
Data Index: 1214099 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1192. Min Act: -0.0001
Data Index: 584482 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1090. Min Act: -0.0001
Data Index: 1431656 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1729. Min Range: -0.1729
Max Act: 0.1376. Min Act: -0.0001
Data Index: 120754 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19