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

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

Neuron 613 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.3528. Min Act: -0.0000

Data Index: 1472339 (Python Code)

Max Activating Token Index: 441

Text #1

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.4004. Min Act: -0.0000

Data Index: 1863 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.3813. Min Act: -0.0000

Data Index: 1588960 (Python Code)

Max Activating Token Index: 534

Text #3

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1490637 (Python Code)

Max Activating Token Index: 348

Text #4

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.3062. Min Act: -0.0000

Data Index: 340950 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.3943. Min Act: -0.0000

Data Index: 1472485 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.3185. Min Act: -0.0000

Data Index: 1093329 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.3079. Min Act: -0.0000

Data Index: 1467385 (Python Code)

Max Activating Token Index: 480

Text #8

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.2099. Min Act: -0.0000

Data Index: 632663 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.1619. Min Act: -0.0000

Data Index: 1553494 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.0490. Min Act: -0.0000

Data Index: 339252 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1527177 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.1470. Min Act: -0.0000

Data Index: 869264 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.2292. Min Act: -0.0000

Data Index: 729500 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.1727. Min Act: -0.0000

Data Index: 301774 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.1611. Min Act: -0.0000

Data Index: 989650 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 2.4004. Min Range: -2.4004

Max Act: 1.9535. Min Act: -0.0000

Data Index: 1618264 (Python Code)

Max Activating Token Index: 298

Text #17

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.0380. Min Act: -0.0000

Data Index: 1076531 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.0165. Min Act: -0.0000

Data Index: 1583204 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 2.4004. Min Range: -2.4004

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1249141 (C4 (Web Text))

Max Activating Token Index: 979