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

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

Neuron 4334 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2784. Min Range: -2.2784

Max Act: 2.2784. Min Act: -0.0000

Data Index: 1292122 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 2.2784. Min Range: -2.2784

Max Act: 2.1993. Min Act: -0.0000

Data Index: 765781 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 2.2784. Min Range: -2.2784

Max Act: 2.0313. Min Act: -0.0000

Data Index: 695040 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.8168. Min Act: -0.0000

Data Index: 1464938 (Python Code)

Max Activating Token Index: 490

Text #4

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.8824. Min Act: -0.0000

Data Index: 275554 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.6986. Min Act: -0.0000

Data Index: 989187 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1419415 (Python Code)

Max Activating Token Index: 811

Text #7

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.7649. Min Act: -0.0000

Data Index: 442909 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.7518. Min Act: -0.0000

Data Index: 264534 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.4959. Min Act: -0.0000

Data Index: 797622 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.6503. Min Act: -0.0000

Data Index: 1398609 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.7346. Min Act: -0.0000

Data Index: 97781 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1427003 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.5593. Min Act: -0.0000

Data Index: 1008760 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.5515. Min Act: -0.0000

Data Index: 597299 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1021906 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.4386. Min Act: -0.0000

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.5047. Min Act: -0.0000

Data Index: 155738 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.4214. Min Act: -0.0000

Data Index: 416453 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 2.2784. Min Range: -2.2784

Max Act: 1.4316. Min Act: -0.0000

Data Index: 853994 (C4 (Web Text))

Max Activating Token Index: 944