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

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

Neuron 503 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: 3.5738. Min Range: -3.5738

Max Act: 3.4506. Min Act: -0.0000

Data Index: 641005 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.4514. Min Act: -0.0000

Data Index: 384446 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.5172. Min Act: -0.0000

Data Index: 1114521 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.5738. Min Act: -0.0000

Data Index: 632880 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.2338. Min Act: -0.0000

Data Index: 446003 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.3680. Min Act: -0.0000

Data Index: 326617 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.1749. Min Act: -0.0000

Data Index: 1155885 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.3162. Min Act: -0.0000

Data Index: 650557 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.1151. Min Act: -0.0000

Data Index: 981685 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.0382. Min Act: -0.0000

Data Index: 998599 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.2954. Min Act: -0.0000

Data Index: 132635 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.9889. Min Act: -0.0000

Data Index: 759545 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.9181. Min Act: -0.0000

Data Index: 350860 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 3.5738. Min Range: -3.5738

Max Act: 3.2348. Min Act: -0.0000

Data Index: 814742 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.7309. Min Act: -0.0000

Data Index: 1304081 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.7563. Min Act: -0.0000

Data Index: 1103512 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.9203. Min Act: -0.0000

Data Index: 929947 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.4621. Min Act: -0.0000

Data Index: 963467 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.7166. Min Act: -0.0000

Data Index: 159928 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 3.5738. Min Range: -3.5738

Max Act: 2.8974. Min Act: -0.0000

Data Index: 186398 (C4 (Web Text))

Max Activating Token Index: 180