Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3766 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7853. Min Act: -0.0002

Data Index: 1350268 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5862. Min Act: -0.0001

Data Index: 310267 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5781. Min Act: -0.0001

Data Index: 463785 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5486. Min Act: -0.0002

Data Index: 66883 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5721. Min Act: -0.0001

Data Index: 383714 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5819. Min Act: -0.0001

Data Index: 1201985 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5352. Min Act: -0.0002

Data Index: 365443 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4448. Min Act: -0.0002

Data Index: 103431 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5180. Min Act: -0.0002

Data Index: 416839 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5170. Min Act: -0.0002

Data Index: 895264 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5343. Min Act: -0.0002

Data Index: 914333 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5517. Min Act: -0.0001

Data Index: 1312183 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5098. Min Act: -0.0001

Data Index: 1234319 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5047. Min Act: -0.0002

Data Index: 889308 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5224. Min Act: -0.0002

Data Index: 1064882 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5362. Min Act: -0.0002

Data Index: 836457 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5184. Min Act: -0.0002

Data Index: 754929 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4829. Min Act: -0.0002

Data Index: 128321 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5243. Min Act: -0.0002

Data Index: 626883 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5082. Min Act: -0.0002

Data Index: 1173685 (C4 (Web Text))

Max Activating Token Index: 51