Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3590 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1232141 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3757. Min Act: -0.0000

Data Index: 127188 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3530. Min Act: -0.0000

Data Index: 433406 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1186536 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3543. Min Act: -0.0001

Data Index: 180828 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3276. Min Act: -0.0000

Data Index: 485590 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2993. Min Act: -0.0000

Data Index: 216530 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3105. Min Act: -0.0001

Data Index: 1373276 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2888. Min Act: -0.0000

Data Index: 780024 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3362. Min Act: -0.0001

Data Index: 70520 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3003. Min Act: -0.0001

Data Index: 257609 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2841. Min Act: -0.0000

Data Index: 115508 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3038. Min Act: -0.0000

Data Index: 403593 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2893. Min Act: -0.0000

Data Index: 340478 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2716. Min Act: -0.0000

Data Index: 326954 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3045. Min Act: -0.0000

Data Index: 272369 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2549. Min Act: -0.0000

Data Index: 398019 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1287342 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2427. Min Act: -0.0001

Data Index: 257824 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.2560. Min Act: -0.0001

Data Index: 573315 (C4 (Web Text))

Max Activating Token Index: 857