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

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

Neuron 4008 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3783. Min Act: -0.0000

Data Index: 226784 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3579. Min Act: -0.0000

Data Index: 71521 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1125377 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1334219 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3037. Min Act: -0.0000

Data Index: 13608 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3159. Min Act: -0.0000

Data Index: 226355 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3462. Min Act: -0.0001

Data Index: 1326582 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3229. Min Act: -0.0001

Data Index: 347375 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3009. Min Act: -0.0001

Data Index: 31237 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3113. Min Act: -0.0000

Data Index: 29306 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3037. Min Act: -0.0000

Data Index: 900489 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2908. Min Act: -0.0001

Data Index: 549051 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2901. Min Act: -0.0000

Data Index: 455676 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2625. Min Act: -0.0001

Data Index: 1123128 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2500. Min Act: -0.0001

Data Index: 571089 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1172770 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2656. Min Act: -0.0000

Data Index: 547402 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2553. Min Act: -0.0000

Data Index: 966661 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2624. Min Act: -0.0001

Data Index: 938471 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2624. Min Act: -0.0001

Data Index: 446666 (C4 (Web Text))

Max Activating Token Index: 340