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

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

Neuron 3995 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3928. Min Act: -0.0000

Data Index: 34316 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1541532 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1169097 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3056. Min Act: -0.0000

Data Index: 382647 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2735. Min Act: -0.0000

Data Index: 468505 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2510. Min Act: -0.0000

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2430. Min Act: -0.0000

Data Index: 403793 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2506. Min Act: -0.0000

Data Index: 209206 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2453. Min Act: -0.0000

Data Index: 407826 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2143. Min Act: -0.0000

Data Index: 914889 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1179955 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1187969 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2356. Min Act: -0.0000

Data Index: 143149 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2207. Min Act: -0.0000

Data Index: 326412 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2234. Min Act: -0.0000

Data Index: 273127 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2471. Min Act: -0.0000

Data Index: 95945 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1180480 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2077. Min Act: -0.0000

Data Index: 269025 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2115. Min Act: -0.0000

Data Index: 985346 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.1946. Min Act: -0.0000

Data Index: 847453 (C4 (Web Text))

Max Activating Token Index: 254