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

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

Neuron 709 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: 1.7256. Min Range: -1.7256

Max Act: 1.7147. Min Act: -0.0001

Data Index: 937909 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.7256. Min Act: -0.0001

Data Index: 471811 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.5615. Min Act: -0.0001

Data Index: 686508 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.6596. Min Act: -0.0001

Data Index: 707909 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4788. Min Act: -0.0001

Data Index: 266461 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4775. Min Act: -0.0001

Data Index: 696689 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4454. Min Act: -0.0001

Data Index: 80862 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4381. Min Act: -0.0001

Data Index: 313787 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4747. Min Act: -0.0001

Data Index: 322077 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.2889. Min Act: -0.0001

Data Index: 1198202 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4317. Min Act: -0.0001

Data Index: 679860 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3835. Min Act: -0.0001

Data Index: 778790 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3345. Min Act: -0.0001

Data Index: 89479 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3734. Min Act: -0.0001

Data Index: 107186 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4520. Min Act: -0.0001

Data Index: 418476 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3429. Min Act: -0.0001

Data Index: 840519 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3686. Min Act: -0.0001

Data Index: 652160 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3248. Min Act: -0.0001

Data Index: 516466 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3532. Min Act: -0.0001

Data Index: 1056506 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3502. Min Act: -0.0001

Data Index: 390541 (C4 (Web Text))

Max Activating Token Index: 97