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

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

Neuron 2680 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1117378 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5052. Min Act: -0.0000

Data Index: 430152 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4493. Min Act: -0.0000

Data Index: 91373 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4619. Min Act: -0.0000

Data Index: 592180 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4482. Min Act: -0.0000

Data Index: 957816 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1031565 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1169439 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4605. Min Act: -0.0000

Data Index: 278869 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4328. Min Act: -0.0000

Data Index: 496928 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1111479 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4545. Min Act: -0.0000

Data Index: 270942 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4216. Min Act: -0.0000

Data Index: 572979 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4401. Min Act: -0.0000

Data Index: 882409 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1342073 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4182. Min Act: -0.0000

Data Index: 121029 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4201. Min Act: -0.0000

Data Index: 148368 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4160. Min Act: -0.0000

Data Index: 588818 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4047. Min Act: -0.0000

Data Index: 564618 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4050. Min Act: -0.0000

Data Index: 554562 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1067146 (C4 (Web Text))

Max Activating Token Index: 43