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

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

Neuron 5462 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.2770. Min Act: -0.0001

Data Index: 612948 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.2066. Min Act: -0.0001

Data Index: 40399 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1837. Min Act: -0.0001

Data Index: 1172545 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9473. Min Act: -0.0001

Data Index: 1350552 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.2299. Min Act: -0.0001

Data Index: 383360 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1953. Min Act: -0.0001

Data Index: 1275656 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.3092. Min Act: -0.0001

Data Index: 716227 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1747. Min Act: -0.0001

Data Index: 403603 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1220. Min Act: -0.0001

Data Index: 887472 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.2221. Min Act: -0.0001

Data Index: 569233 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1984. Min Act: -0.0001

Data Index: 176881 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0302. Min Act: -0.0001

Data Index: 1235890 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.2299. Min Act: -0.0001

Data Index: 390651 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9361. Min Act: -0.0001

Data Index: 309227 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0291. Min Act: -0.0002

Data Index: 622208 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9562. Min Act: -0.0001

Data Index: 548709 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0174. Min Act: -0.0001

Data Index: 458039 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 1.3092. Min Range: -1.3092

Max Act: 0.9278. Min Act: -0.0001

Data Index: 324441 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0795. Min Act: -0.0001

Data Index: 405997 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0468. Min Act: -0.0001

Data Index: 419353 (C4 (Web Text))

Max Activating Token Index: 816