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

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

Neuron 3210 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6617. Min Act: -0.0001

Data Index: 448816 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6361. Min Act: -0.0001

Data Index: 595633 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6340. Min Act: -0.0001

Data Index: 1236319 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6788. Min Act: -0.0001

Data Index: 919201 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5970. Min Act: -0.0001

Data Index: 410183 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5391. Min Act: -0.0001

Data Index: 1344082 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5346. Min Act: -0.0001

Data Index: 1099148 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5387. Min Act: -0.0001

Data Index: 1224866 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6112. Min Act: -0.0001

Data Index: 181947 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5373. Min Act: -0.0001

Data Index: 1119374 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4455. Min Act: -0.0001

Data Index: 735056 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4909. Min Act: -0.0001

Data Index: 615080 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4879. Min Act: -0.0001

Data Index: 666940 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.3559. Min Act: -0.0001

Data Index: 657891 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.3805. Min Act: -0.0001

Data Index: 274807 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5692. Min Act: -0.0001

Data Index: 215161 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5979. Min Act: -0.0001

Data Index: 81492 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4196. Min Act: -0.0001

Data Index: 475373 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4994. Min Act: -0.0001

Data Index: 886907 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4536. Min Act: -0.0001

Data Index: 449795 (C4 (Web Text))

Max Activating Token Index: 444