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

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

Neuron 5815 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1423420 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1614273 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1364167 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1599165 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1624189 (Python Code)

Max Activating Token Index: 508

Text #5

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1536742 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3722. Min Act: -0.0000

Data Index: 838256 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1089971 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3409. Min Act: -0.0000

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1625607 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3381. Min Act: -0.0000

Data Index: 473064 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1412349 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1581547 (Python Code)

Max Activating Token Index: 931

Text #13

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1464607 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1408537 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3108. Min Act: -0.0000

Data Index: 126638 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.2950. Min Act: -0.0000

Data Index: 54002 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1640625 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1386816 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 0.5631. Min Range: -0.5631

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1519698 (Python Code)

Max Activating Token Index: 332