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

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

Neuron 5376 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.6037. Min Act: -0.0000

Data Index: 661503 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.6712. Min Act: -0.0000

Data Index: 1060678 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.6543. Min Act: -0.0001

Data Index: 129734 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.3822. Min Act: -0.0000

Data Index: 197688 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.5088. Min Act: -0.0000

Data Index: 851446 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.4541. Min Act: -0.0000

Data Index: 968583 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.5719. Min Act: -0.0000

Data Index: 918634 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.4671. Min Act: -0.0000

Data Index: 647085 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.1533. Min Act: -0.0000

Data Index: 549311 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.3362. Min Act: -0.0000

Data Index: 493151 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.4431. Min Act: -0.0001

Data Index: 1300457 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.3288. Min Act: -0.0000

Data Index: 1209868 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.4183. Min Act: -0.0000

Data Index: 307322 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.3652. Min Act: -0.0000

Data Index: 648576 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.3080. Min Act: -0.0000

Data Index: 777561 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.0278. Min Act: -0.0000

Data Index: 689724 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.0547. Min Act: -0.0001

Data Index: 862250 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.0470. Min Act: -0.0000

Data Index: 549975 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.0145. Min Act: -0.0000

Data Index: 130346 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 2.6712. Min Range: -2.6712

Max Act: 2.1236. Min Act: -0.0000

Data Index: 363509 (C4 (Web Text))

Max Activating Token Index: 173