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

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

Neuron 535 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: 2.3192. Min Range: -2.3192

Max Act: 2.3192. Min Act: -0.0002

Data Index: 1221682 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 2.3192. Min Range: -2.3192

Max Act: 2.1445. Min Act: -0.0002

Data Index: 480494 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.9360. Min Act: -0.0002

Data Index: 1334914 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8484. Min Act: -0.0002

Data Index: 304683 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8675. Min Act: -0.0002

Data Index: 1351422 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7649. Min Act: -0.0002

Data Index: 547618 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.6353. Min Act: -0.0002

Data Index: 927269 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.6185. Min Act: -0.0002

Data Index: 591394 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.5599. Min Act: -0.0002

Data Index: 99162 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.5968. Min Act: -0.0002

Data Index: 401824 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7585. Min Act: -0.0002

Data Index: 588905 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.6566. Min Act: -0.0002

Data Index: 1343990 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.5950. Min Act: -0.0002

Data Index: 892533 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.6138. Min Act: -0.0002

Data Index: 233461 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.5585. Min Act: -0.0002

Data Index: 646554 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.5424. Min Act: -0.0002

Data Index: 854949 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.5427. Min Act: -0.0002

Data Index: 1138624 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.4537. Min Act: -0.0002

Data Index: 56667 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.4154. Min Act: -0.0002

Data Index: 509066 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.4018. Min Act: -0.0002

Data Index: 1143877 (C4 (Web Text))

Max Activating Token Index: 195