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

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

Neuron 3713 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: 1.0306. Min Range: -1.0306

Max Act: 1.0306. Min Act: -0.0000

Data Index: 244920 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9581. Min Act: -0.0000

Data Index: 784020 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8965. Min Act: -0.0000

Data Index: 899398 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8324. Min Act: -0.0000

Data Index: 920027 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8279. Min Act: -0.0000

Data Index: 200883 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8270. Min Act: -0.0000

Data Index: 502969 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8485. Min Act: -0.0000

Data Index: 102192 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7837. Min Act: -0.0000

Data Index: 327433 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8009. Min Act: -0.0000

Data Index: 712858 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7876. Min Act: -0.0000

Data Index: 189543 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7466. Min Act: -0.0000

Data Index: 701485 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6945. Min Act: -0.0000

Data Index: 183360 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1263021 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7459. Min Act: -0.0000

Data Index: 220998 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6955. Min Act: -0.0000

Data Index: 623349 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6670. Min Act: -0.0000

Data Index: 83057 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6714. Min Act: -0.0000

Data Index: 980572 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6645. Min Act: -0.0000

Data Index: 289236 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1197936 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6047. Min Act: -0.0000

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 714