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

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

Neuron 213 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.8575. Min Act: -0.0000

Data Index: 26356 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.3663. Min Act: -0.0000

Data Index: 1172855 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.4696. Min Act: -0.0000

Data Index: 410823 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.2555. Min Act: -0.0000

Data Index: 1070189 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.2061. Min Act: 0.0000

Data Index: 267075 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.0585. Min Act: 0.0000

Data Index: 1048666 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.1512. Min Act: -0.0000

Data Index: 93811 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.1510. Min Act: -0.0000

Data Index: 113689 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.1123. Min Act: -0.0000

Data Index: 938311 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.0972. Min Act: -0.0000

Data Index: 1023109 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 2.8575. Min Range: -2.8575

Max Act: 1.9490. Min Act: -0.0000

Data Index: 229929 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.0755. Min Act: -0.0000

Data Index: 1000403 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.0335. Min Act: -0.0000

Data Index: 52426 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 2.8575. Min Range: -2.8575

Max Act: 2.0116. Min Act: -0.0000

Data Index: 1002847 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 2.8575. Min Range: -2.8575

Max Act: 1.9682. Min Act: -0.0000

Data Index: 1012546 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 2.8575. Min Range: -2.8575

Max Act: 1.7842. Min Act: -0.0000

Data Index: 291260 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 2.8575. Min Range: -2.8575

Max Act: 1.8382. Min Act: -0.0000

Data Index: 517387 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 2.8575. Min Range: -2.8575

Max Act: 1.7453. Min Act: -0.0000

Data Index: 50160 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 2.8575. Min Range: -2.8575

Max Act: 1.7518. Min Act: 0.0000

Data Index: 790196 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 2.8575. Min Range: -2.8575

Max Act: 1.7433. Min Act: -0.0000

Data Index: 13469 (C4 (Web Text))

Max Activating Token Index: 59