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

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

Neuron 4400 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7787. Min Range: -2.7787

Max Act: 2.7787. Min Act: -0.0000

Data Index: 947734 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 2.7787. Min Range: -2.7787

Max Act: 2.4315. Min Act: -0.0000

Data Index: 1052495 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 2.7787. Min Range: -2.7787

Max Act: 2.3800. Min Act: -0.0000

Data Index: 1002100 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.9719. Min Act: -0.0000

Data Index: 158639 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 2.7787. Min Range: -2.7787

Max Act: 2.1841. Min Act: -0.0000

Data Index: 174549 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.9619. Min Act: -0.0000

Data Index: 1296119 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.8632. Min Act: -0.0000

Data Index: 1644016 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.9704. Min Act: -0.0000

Data Index: 1549751 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 2.7787. Min Range: -2.7787

Max Act: 2.1842. Min Act: -0.0000

Data Index: 815253 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.7319. Min Act: -0.0000

Data Index: 327576 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.8770. Min Act: -0.0000

Data Index: 1334635 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.8888. Min Act: -0.0000

Data Index: 1466471 (Python Code)

Max Activating Token Index: 153

Text #12

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.7763. Min Act: -0.0000

Data Index: 768274 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.8661. Min Act: -0.0000

Data Index: 1404124 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.9775. Min Act: -0.0000

Data Index: 1502574 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.7427. Min Act: -0.0000

Data Index: 1519035 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.9202. Min Act: -0.0000

Data Index: 1299425 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.6886. Min Act: -0.0000

Data Index: 1505745 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1619331 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 2.7787. Min Range: -2.7787

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1614837 (Python Code)

Max Activating Token Index: 89