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

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

Neuron 1592 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.3312. Min Act: -0.0000

Data Index: 307652 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.9399. Min Act: -0.0000

Data Index: 724458 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.8776. Min Act: -0.0000

Data Index: 528220 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.8443. Min Act: -0.0000

Data Index: 1010404 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.6201. Min Act: -0.0000

Data Index: 1216354 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.6291. Min Act: -0.0000

Data Index: 19879 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.5596. Min Act: -0.0000

Data Index: 207047 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.4650. Min Act: -0.0000

Data Index: 846228 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.4932. Min Act: -0.0000

Data Index: 884977 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.4279. Min Act: -0.0000

Data Index: 506472 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1019345 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.4927. Min Act: -0.0000

Data Index: 230880 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.3648. Min Act: -0.0000

Data Index: 1167798 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.2606. Min Act: -0.0000

Data Index: 998562 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.2617. Min Act: -0.0000

Data Index: 895808 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.3402. Min Act: -0.0000

Data Index: 1201748 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.3215. Min Act: -0.0000

Data Index: 152490 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.3098. Min Act: -0.0000

Data Index: 311022 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.3518. Min Act: -0.0000

Data Index: 386989 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1339096 (C4 (Web Text))

Max Activating Token Index: 93