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

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

Neuron 2330 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: 1.1340. Min Range: -1.1340

Max Act: 1.1340. Min Act: -0.0000

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.9875. Min Act: -0.0000

Data Index: 334449 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1236483 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.8152. Min Act: -0.0000

Data Index: 501014 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.8678. Min Act: -0.0000

Data Index: 6386 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1305960 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.7748. Min Act: -0.0000

Data Index: 487256 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.7550. Min Act: -0.0000

Data Index: 451571 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.7266. Min Act: -0.0000

Data Index: 851476 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6637. Min Act: -0.0000

Data Index: 116935 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1568546 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6920. Min Act: -0.0000

Data Index: 974107 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.7496. Min Act: -0.0000

Data Index: 817074 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1655429 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1362857 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1509562 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6622. Min Act: -0.0000

Data Index: 264847 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1639539 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1419952 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 1.1340. Min Range: -1.1340

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1060159 (C4 (Web Text))

Max Activating Token Index: 129