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

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

Neuron 2593 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: 2.6322. Min Range: -2.6322

Max Act: 2.6322. Min Act: -0.0000

Data Index: 319677 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.3745. Min Act: -0.0000

Data Index: 724746 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.1312. Min Act: -0.0000

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.3001. Min Act: -0.0000

Data Index: 602545 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.3302. Min Act: -0.0000

Data Index: 409611 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.4306. Min Act: -0.0000

Data Index: 1322209 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.2275. Min Act: -0.0000

Data Index: 222770 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.0384. Min Act: -0.0000

Data Index: 407440 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.0821. Min Act: -0.0000

Data Index: 535249 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.0609. Min Act: -0.0000

Data Index: 107395 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.0622. Min Act: -0.0000

Data Index: 127719 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.1429. Min Act: -0.0000

Data Index: 1058141 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.0078. Min Act: -0.0000

Data Index: 380999 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 2.6322. Min Range: -2.6322

Max Act: 1.9828. Min Act: -0.0000

Data Index: 328840 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.0093. Min Act: -0.0000

Data Index: 559868 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 2.6322. Min Range: -2.6322

Max Act: 1.8656. Min Act: -0.0000

Data Index: 1155559 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 2.6322. Min Range: -2.6322

Max Act: 1.9533. Min Act: -0.0000

Data Index: 46620 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.6322. Min Range: -2.6322

Max Act: 1.7663. Min Act: -0.0000

Data Index: 626651 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.6322. Min Range: -2.6322

Max Act: 1.9507. Min Act: -0.0000

Data Index: 440253 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 2.6322. Min Range: -2.6322

Max Act: 2.0533. Min Act: -0.0000

Data Index: 431601 (C4 (Web Text))

Max Activating Token Index: 458