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

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

Neuron 2854 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1192282 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2337. Min Act: -0.0001

Data Index: 404015 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2034. Min Act: -0.0001

Data Index: 323503 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2060. Min Act: -0.0001

Data Index: 943541 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1320624 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2146. Min Act: -0.0000

Data Index: 298032 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2028. Min Act: -0.0000

Data Index: 517625 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1015078 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2026. Min Act: -0.0000

Data Index: 846316 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1104322 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1997. Min Act: -0.0000

Data Index: 790795 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1846. Min Act: -0.0001

Data Index: 649434 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2048. Min Act: -0.0001

Data Index: 426282 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1893. Min Act: -0.0001

Data Index: 919830 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.2174. Min Act: -0.0000

Data Index: 529510 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1156891 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1323337 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1832. Min Act: -0.0000

Data Index: 169567 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.2686. Min Range: -0.2686

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1324555 (C4 (Web Text))

Max Activating Token Index: 192