Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1460 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.8060. Min Act: -0.0003

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.5396. Min Act: -0.0003

Data Index: 141400 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.5312. Min Act: -0.0002

Data Index: 806951 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.5407. Min Act: -0.0002

Data Index: 81205 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.3415. Min Act: -0.0002

Data Index: 408075 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.2922. Min Act: -0.0002

Data Index: 1246850 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.2650. Min Act: -0.0002

Data Index: 1048334 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1908. Min Act: -0.0002

Data Index: 505043 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1874. Min Act: -0.0002

Data Index: 386705 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.2192. Min Act: -0.0003

Data Index: 783119 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1614. Min Act: -0.0003

Data Index: 1276574 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1565. Min Act: -0.0002

Data Index: 147505 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1225. Min Act: -0.0003

Data Index: 1123273 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1348. Min Act: -0.0002

Data Index: 1127249 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1314. Min Act: -0.0002

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1018. Min Act: -0.0003

Data Index: 697205 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0733. Min Act: -0.0003

Data Index: 947546 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0700. Min Act: -0.0003

Data Index: 1347679 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0365. Min Act: -0.0003

Data Index: 881466 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0673. Min Act: -0.0003

Data Index: 294355 (C4 (Web Text))

Max Activating Token Index: 245