Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4688 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1275. Min Range: -2.1275

Max Act: 2.0697. Min Act: -0.0000

Data Index: 1265743 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 2.1275. Min Range: -2.1275

Max Act: 2.1275. Min Act: -0.0000

Data Index: 1237486 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.9794. Min Act: -0.0000

Data Index: 365517 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.8627. Min Act: -0.0000

Data Index: 836100 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.9168. Min Act: -0.0000

Data Index: 687440 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.8785. Min Act: -0.0000

Data Index: 310076 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7619. Min Act: -0.0000

Data Index: 701243 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.8472. Min Act: -0.0000

Data Index: 943192 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.8441. Min Act: -0.0000

Data Index: 542134 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1278177 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7617. Min Act: -0.0000

Data Index: 1206080 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7510. Min Act: -0.0000

Data Index: 450564 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7392. Min Act: -0.0000

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7613. Min Act: -0.0000

Data Index: 621824 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.6463. Min Act: -0.0000

Data Index: 20213 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.8340. Min Act: -0.0000

Data Index: 396908 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1038994 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.7399. Min Act: -0.0000

Data Index: 25546 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.5494. Min Act: -0.0000

Data Index: 699998 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 2.1275. Min Range: -2.1275

Max Act: 1.6920. Min Act: -0.0000

Data Index: 97906 (C4 (Web Text))

Max Activating Token Index: 221