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

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

Neuron 3398 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.5289. Min Act: -0.0001

Data Index: 1639238 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.4830. Min Act: -0.0001

Data Index: 1365181 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2905. Min Act: -0.0001

Data Index: 1472252 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.3088. Min Act: -0.0001

Data Index: 1637509 (Python Code)

Max Activating Token Index: 449

Text #4

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2925. Min Act: -0.0001

Data Index: 1490459 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2878. Min Act: -0.0001

Data Index: 1380533 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.4236. Min Act: -0.0001

Data Index: 1567364 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2559. Min Act: -0.0001

Data Index: 1570814 (Python Code)

Max Activating Token Index: 805

Text #8

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.3778. Min Act: -0.0001

Data Index: 1452232 (Python Code)

Max Activating Token Index: 832

Text #9

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2220. Min Act: -0.0001

Data Index: 1448411 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.3610. Min Act: -0.0001

Data Index: 1563956 (Python Code)

Max Activating Token Index: 477

Text #11

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2048. Min Act: -0.0001

Data Index: 1634688 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.1267. Min Act: -0.0001

Data Index: 1468724 (Python Code)

Max Activating Token Index: 683

Text #13

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2756. Min Act: -0.0001

Data Index: 1533400 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.0456. Min Act: -0.0001

Data Index: 1486681 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.1141. Min Act: -0.0001

Data Index: 1413314 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.1195. Min Act: -0.0001

Data Index: 1605319 (Python Code)

Max Activating Token Index: 891

Text #17

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2283. Min Act: -0.0001

Data Index: 1634092 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.0699. Min Act: -0.0001

Data Index: 1471695 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 3.5289. Min Range: -3.5289

Max Act: 3.2246. Min Act: -0.0001

Data Index: 1599056 (Python Code)

Max Activating Token Index: 811