Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 938 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.3515. Min Act: -0.0003

Data Index: 745240 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0370. Min Act: -0.0003

Data Index: 1210740 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0932. Min Act: -0.0003

Data Index: 1243050 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0502. Min Act: -0.0003

Data Index: 582973 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0576. Min Act: -0.0003

Data Index: 1038594 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0499. Min Act: -0.0003

Data Index: 319500 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8890. Min Act: -0.0003

Data Index: 309256 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0249. Min Act: -0.0003

Data Index: 440930 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.1367. Min Act: -0.0003

Data Index: 750034 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8852. Min Act: -0.0003

Data Index: 345235 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9621. Min Act: -0.0003

Data Index: 635605 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9407. Min Act: -0.0003

Data Index: 126268 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0457. Min Act: -0.0003

Data Index: 91500 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8490. Min Act: -0.0003

Data Index: 643575 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9265. Min Act: -0.0003

Data Index: 269660 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9388. Min Act: -0.0003

Data Index: 967206 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9377. Min Act: -0.0003

Data Index: 46104 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8489. Min Act: -0.0003

Data Index: 192608 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8769. Min Act: -0.0003

Data Index: 817023 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8151. Min Act: -0.0003

Data Index: 817926 (C4 (Web Text))

Max Activating Token Index: 316