Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 114 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.4091. Min Act: -0.0002

Data Index: 1599911 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3239. Min Act: -0.0002

Data Index: 1461061 (Python Code)

Max Activating Token Index: 813

Text #2

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3630. Min Act: -0.0002

Data Index: 595530 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2921. Min Act: -0.0002

Data Index: 1570230 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.3034. Min Act: -0.0002

Data Index: 904063 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2793. Min Act: -0.0002

Data Index: 1559303 (Python Code)

Max Activating Token Index: 656

Text #6

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2725. Min Act: -0.0002

Data Index: 1366642 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2692. Min Act: -0.0002

Data Index: 1603016 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2619. Min Act: -0.0002

Data Index: 415230 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2404. Min Act: -0.0002

Data Index: 1643062 (Python Code)

Max Activating Token Index: 714

Text #10

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2353. Min Act: -0.0002

Data Index: 449195 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2256. Min Act: -0.0002

Data Index: 1373730 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2316. Min Act: -0.0002

Data Index: 801649 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2200. Min Act: -0.0002

Data Index: 1391375 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2183. Min Act: -0.0002

Data Index: 1302518 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2120. Min Act: -0.0002

Data Index: 1379307 (Python Code)

Max Activating Token Index: 717

Text #16

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2228. Min Act: -0.0002

Data Index: 1362023 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2035. Min Act: -0.0002

Data Index: 1404759 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2258. Min Act: -0.0002

Data Index: 1373214 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 1.4091. Min Range: -1.4091

Max Act: 1.2098. Min Act: -0.0002

Data Index: 1435557 (Python Code)

Max Activating Token Index: 1013