Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 798 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2364. Min Act: -0.0000

Data Index: 964138 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1940. Min Act: -0.0000

Data Index: 848183 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2180. Min Act: -0.0000

Data Index: 867885 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2315. Min Act: -0.0000

Data Index: 42432 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1411427 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1004036 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2307. Min Act: -0.0000

Data Index: 521566 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2258. Min Act: -0.0000

Data Index: 41494 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1969. Min Act: -0.0000

Data Index: 132953 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1013203 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1455419 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2076. Min Act: -0.0000

Data Index: 826905 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1283450 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1757. Min Act: -0.0000

Data Index: 117067 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1012130 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1269838 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1920. Min Act: -0.0000

Data Index: 520686 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1386451 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1186747 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1013715 (C4 (Web Text))

Max Activating Token Index: 466