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

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

Neuron 1701 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1317733 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1331114 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2336. Min Act: -0.0000

Data Index: 521184 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1467536 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1113646 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2186. Min Act: -0.0000

Data Index: 392643 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1033445 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2167. Min Act: -0.0000

Data Index: 645322 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1538302 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1456778 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1395309 (Python Code)

Max Activating Token Index: 327

Text #11

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1624546 (Python Code)

Max Activating Token Index: 187

Text #12

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1945. Min Act: -0.0000

Data Index: 298237 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2035. Min Act: -0.0000

Data Index: 973769 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1471773 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1381191 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1444178 (Python Code)

Max Activating Token Index: 491

Text #17

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1970. Min Act: -0.0000

Data Index: 725651 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1873. Min Act: -0.0000

Data Index: 78269 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1776. Min Act: -0.0000

Data Index: 73385 (C4 (Web Text))

Max Activating Token Index: 54