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

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

Neuron 3467 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1334113 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0618. Min Act: -0.0001

Data Index: 610872 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1283710 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0493. Min Act: -0.0001

Data Index: 364417 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0528. Min Act: -0.0001

Data Index: 785105 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0480. Min Act: -0.0001

Data Index: 108399 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0470. Min Act: -0.0001

Data Index: 836266 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1256105 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1148808 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1065758 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0435. Min Act: -0.0001

Data Index: 610072 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1175322 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0441. Min Act: -0.0001

Data Index: 428754 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0448. Min Act: -0.0001

Data Index: 678591 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1352227 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0424. Min Act: -0.0001

Data Index: 472696 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0418. Min Act: -0.0001

Data Index: 58088 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0437. Min Act: -0.0001

Data Index: 344782 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0450. Min Act: -0.0001

Data Index: 476893 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1183919 (C4 (Web Text))

Max Activating Token Index: 913