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

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

Neuron 3517 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.5913. Min Act: -0.0001

Data Index: 277481 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.6148. Min Act: -0.0001

Data Index: 472652 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.5952. Min Act: -0.0001

Data Index: 561204 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.6385. Min Act: -0.0001

Data Index: 442108 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.4887. Min Act: -0.0001

Data Index: 756898 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.5053. Min Act: -0.0001

Data Index: 1287282 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.5509. Min Act: -0.0001

Data Index: 1228282 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.4975. Min Act: -0.0001

Data Index: 594636 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.6072. Min Act: -0.0001

Data Index: 1306880 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.6480. Min Act: -0.0001

Data Index: 169990 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.5390. Min Act: -0.0001

Data Index: 192916 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.3998. Min Act: -0.0001

Data Index: 969159 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.4826. Min Act: -0.0001

Data Index: 993378 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.4403. Min Act: -0.0001

Data Index: 317947 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.5700. Min Act: -0.0001

Data Index: 113549 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.5550. Min Act: -0.0001

Data Index: 771500 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.4928. Min Act: -0.0001

Data Index: 527712 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.4002. Min Act: -0.0001

Data Index: 187366 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.4344. Min Act: -0.0001

Data Index: 422768 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 1.6480. Min Range: -1.6480

Max Act: 1.3870. Min Act: -0.0001

Data Index: 1254553 (C4 (Web Text))

Max Activating Token Index: 80