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

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

Neuron 2564 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.6363. Min Act: -0.0000

Data Index: 1121939 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8738. Min Act: -0.0000

Data Index: 1068997 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.5162. Min Act: -0.0000

Data Index: 1122040 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.3411. Min Act: -0.0000

Data Index: 759393 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.4385. Min Act: -0.0000

Data Index: 583891 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.1990. Min Act: 0.0000

Data Index: 655250 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.0369. Min Act: -0.0000

Data Index: 611682 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.8995. Min Act: -0.0000

Data Index: 120087 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.9586. Min Act: -0.0000

Data Index: 1194814 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.9474. Min Act: -0.0000

Data Index: 120621 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.9288. Min Act: -0.0000

Data Index: 960360 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.8365. Min Act: -0.0000

Data Index: 1054737 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.9037. Min Act: -0.0000

Data Index: 1064469 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.7130. Min Act: -0.0000

Data Index: 355925 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.8054. Min Act: -0.0000

Data Index: 1222157 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.7960. Min Act: -0.0000

Data Index: 248340 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.7009. Min Act: -0.0000

Data Index: 905762 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1021343 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.7876. Min Act: -0.0000

Data Index: 747781 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 2.8738. Min Range: -2.8738

Max Act: 1.6881. Min Act: -0.0000

Data Index: 268331 (C4 (Web Text))

Max Activating Token Index: 853