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

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

Neuron 5256 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0002

Data Index: 743241 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1242532 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0557. Min Act: -0.0002

Data Index: 64331 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1173912 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0538. Min Act: -0.0002

Data Index: 35264 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1049273 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0493. Min Act: -0.0002

Data Index: 966572 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0484. Min Act: -0.0002

Data Index: 777478 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0463. Min Act: -0.0002

Data Index: 204628 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0480. Min Act: -0.0002

Data Index: 10150 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0485. Min Act: -0.0002

Data Index: 9478 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1120639 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1128059 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0456. Min Act: -0.0002

Data Index: 986992 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0457. Min Act: -0.0002

Data Index: 836261 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0441. Min Act: -0.0002

Data Index: 122069 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0433. Min Act: -0.0002

Data Index: 90309 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1183669 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0444. Min Act: -0.0002

Data Index: 366628 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0435. Min Act: -0.0002

Data Index: 582512 (C4 (Web Text))

Max Activating Token Index: 750