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

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

Neuron 2604 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.4000. Min Act: -0.0000

Data Index: 1194481 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.4084. Min Act: -0.0001

Data Index: 1588778 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.3590. Min Act: -0.0000

Data Index: 47221 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.4547. Min Act: -0.0000

Data Index: 524066 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.3732. Min Act: -0.0000

Data Index: 916511 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.3229. Min Act: -0.0000

Data Index: 1108603 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.3158. Min Act: -0.0001

Data Index: 762988 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2905. Min Act: -0.0000

Data Index: 1273343 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2846. Min Act: -0.0001

Data Index: 1521180 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2366. Min Act: -0.0000

Data Index: 177050 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2546. Min Act: -0.0001

Data Index: 1604001 (Python Code)

Max Activating Token Index: 340

Text #11

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1268498 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2906. Min Act: -0.0000

Data Index: 802264 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2571. Min Act: -0.0000

Data Index: 815780 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1072212 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1583. Min Act: -0.0000

Data Index: 36659 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1450112 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.1892. Min Act: -0.0000

Data Index: 456804 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1389266 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 1.4547. Min Range: -1.4547

Max Act: 1.3275. Min Act: -0.0000

Data Index: 590039 (C4 (Web Text))

Max Activating Token Index: 343