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

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

Neuron 4687 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.5416. Min Act: -0.0000

Data Index: 904289 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3893. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.4008. Min Act: -0.0000

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3845. Min Act: -0.0000

Data Index: 928017 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3713. Min Act: -0.0000

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3530. Min Act: -0.0000

Data Index: 552449 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1270442 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3318. Min Act: 0.0000

Data Index: 1246449 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3287. Min Act: 0.0000

Data Index: 192589 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3294. Min Act: 0.0000

Data Index: 55470 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3501. Min Act: -0.0000

Data Index: 739438 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3366. Min Act: -0.0000

Data Index: 893288 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3467. Min Act: -0.0000

Data Index: 490793 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3448. Min Act: 0.0000

Data Index: 94648 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3309. Min Act: 0.0001

Data Index: 545338 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3131. Min Act: -0.0000

Data Index: 539883 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3096. Min Act: -0.0000

Data Index: 490323 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3120. Min Act: 0.0000

Data Index: 780685 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3014. Min Act: -0.0000

Data Index: 274793 (C4 (Web Text))

Max Activating Token Index: 399