Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2476 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.2076. Min Act: -0.0003

Data Index: 1198352 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1772. Min Act: -0.0003

Data Index: 473087 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1681. Min Act: -0.0003

Data Index: 636490 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1670. Min Act: -0.0003

Data Index: 1334583 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1523. Min Act: -0.0003

Data Index: 44997 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1529. Min Act: -0.0003

Data Index: 183287 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1572. Min Act: -0.0003

Data Index: 864570 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1626. Min Act: -0.0003

Data Index: 230497 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1447. Min Act: -0.0003

Data Index: 647342 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1438. Min Act: -0.0003

Data Index: 1356452 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1433. Min Act: -0.0003

Data Index: 134861 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1531. Min Act: -0.0003

Data Index: 523017 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1466. Min Act: -0.0003

Data Index: 324014 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1514. Min Act: -0.0003

Data Index: 764270 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1389. Min Act: -0.0003

Data Index: 898465 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1414. Min Act: -0.0003

Data Index: 445219 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1435. Min Act: -0.0003

Data Index: 510151 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1397. Min Act: -0.0003

Data Index: 390693 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1228. Min Act: -0.0003

Data Index: 913199 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1232. Min Act: -0.0003

Data Index: 673854 (C4 (Web Text))

Max Activating Token Index: 867