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

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

Neuron 1736 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.4376. Min Act: -0.0001

Data Index: 493036 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.3038. Min Act: -0.0001

Data Index: 1090425 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.2257. Min Act: -0.0000

Data Index: 175936 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.2033. Min Act: -0.0001

Data Index: 1275952 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0619. Min Act: -0.0001

Data Index: 422528 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1154914 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0130. Min Act: -0.0001

Data Index: 909238 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1087555 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 1.4376. Min Range: -1.4376

Max Act: 1.0022. Min Act: -0.0000

Data Index: 978296 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9745. Min Act: -0.0001

Data Index: 45189 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9819. Min Act: -0.0000

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9492. Min Act: -0.0001

Data Index: 317360 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9444. Min Act: -0.0000

Data Index: 761140 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.8822. Min Act: -0.0000

Data Index: 180848 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.8559. Min Act: -0.0001

Data Index: 1220726 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9771. Min Act: -0.0001

Data Index: 581295 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1087997 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.9639. Min Act: -0.0001

Data Index: 265943 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.8358. Min Act: -0.0001

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.4376. Min Range: -1.4376

Max Act: 0.7791. Min Act: -0.0001

Data Index: 687631 (C4 (Web Text))

Max Activating Token Index: 295