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

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

Neuron 1961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0288. Min Range: -4.0288

Max Act: 4.0288. Min Act: -0.0000

Data Index: 562057 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.5135. Min Act: -0.0000

Data Index: 925327 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.3857. Min Act: -0.0000

Data Index: 897523 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.2216. Min Act: -0.0000

Data Index: 208039 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.0282. Min Act: -0.0000

Data Index: 5934 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.9970. Min Act: -0.0000

Data Index: 1253077 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.9398. Min Act: -0.0000

Data Index: 287210 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.1961. Min Act: -0.0000

Data Index: 721201 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.1615. Min Act: -0.0000

Data Index: 1267930 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.8911. Min Act: -0.0000

Data Index: 24690 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.9130. Min Act: -0.0000

Data Index: 1316607 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.5637. Min Act: -0.0000

Data Index: 1346427 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.8155. Min Act: -0.0000

Data Index: 716398 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.7964. Min Act: -0.0000

Data Index: 1088985 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.5346. Min Act: -0.0000

Data Index: 179409 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.7963. Min Act: -0.0000

Data Index: 653388 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.6415. Min Act: -0.0000

Data Index: 557966 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.7613. Min Act: -0.0001

Data Index: 127685 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 4.0288. Min Range: -4.0288

Max Act: 3.0258. Min Act: -0.0000

Data Index: 1067612 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 4.0288. Min Range: -4.0288

Max Act: 2.7382. Min Act: -0.0000

Data Index: 549824 (C4 (Web Text))

Max Activating Token Index: 534