Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.6863. Min Act: -0.0001

Data Index: 601420 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5278. Min Act: -0.0001

Data Index: 104071 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5177. Min Act: -0.0001

Data Index: 232678 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1311936 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.5028. Min Act: -0.0001

Data Index: 76287 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4948. Min Act: -0.0001

Data Index: 150641 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4920. Min Act: -0.0001

Data Index: 114189 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4606. Min Act: -0.0000

Data Index: 988446 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4579. Min Act: -0.0001

Data Index: 15469 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4181. Min Act: -0.0001

Data Index: 671270 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4447. Min Act: -0.0001

Data Index: 1343457 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4593. Min Act: -0.0000

Data Index: 403618 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4346. Min Act: -0.0001

Data Index: 1073460 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4231. Min Act: -0.0001

Data Index: 712449 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4242. Min Act: -0.0001

Data Index: 901391 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4105. Min Act: -0.0001

Data Index: 922126 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4361. Min Act: -0.0001

Data Index: 534000 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4204. Min Act: -0.0000

Data Index: 556685 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4181. Min Act: -0.0001

Data Index: 326831 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.6863. Min Range: -0.6863

Max Act: 0.4288. Min Act: -0.0001

Data Index: 978028 (C4 (Web Text))

Max Activating Token Index: 778