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

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

Neuron 344 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: 2.0091. Min Range: -2.0091

Max Act: 2.0091. Min Act: -0.0000

Data Index: 816900 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.7925. Min Act: -0.0000

Data Index: 1310492 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.6753. Min Act: -0.0000

Data Index: 1134955 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.7341. Min Act: -0.0000

Data Index: 602941 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.6626. Min Act: -0.0000

Data Index: 1324932 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1113769 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.4903. Min Act: -0.0000

Data Index: 386228 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.4016. Min Act: -0.0000

Data Index: 803044 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.4693. Min Act: -0.0000

Data Index: 857770 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.3296. Min Act: -0.0000

Data Index: 804507 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1235131 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.2821. Min Act: -0.0000

Data Index: 244947 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.3632. Min Act: -0.0001

Data Index: 1184120 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1441732 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.2225. Min Act: -0.0000

Data Index: 998513 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.2598. Min Act: -0.0000

Data Index: 108372 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.2515. Min Act: -0.0000

Data Index: 339543 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.2335. Min Act: -0.0000

Data Index: 366115 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1101467 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 2.0091. Min Range: -2.0091

Max Act: 1.2294. Min Act: -0.0000

Data Index: 820466 (C4 (Web Text))

Max Activating Token Index: 714