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

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

Neuron 783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4542. Min Act: -0.0000

Data Index: 825546 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1033480 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3353. Min Act: -0.0000

Data Index: 728682 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2896. Min Act: -0.0000

Data Index: 832218 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2973. Min Act: -0.0000

Data Index: 457386 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2835. Min Act: -0.0000

Data Index: 765301 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2818. Min Act: -0.0000

Data Index: 665678 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2653. Min Act: -0.0000

Data Index: 88316 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2735. Min Act: -0.0001

Data Index: 1113518 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2725. Min Act: -0.0000

Data Index: 683098 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1242937 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2378. Min Act: -0.0000

Data Index: 508023 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2273. Min Act: -0.0000

Data Index: 178337 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2274. Min Act: -0.0001

Data Index: 88552 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2104. Min Act: -0.0000

Data Index: 58963 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1174254 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1284134 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1304685 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2290. Min Act: -0.0001

Data Index: 1211996 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.2306. Min Act: -0.0000

Data Index: 50363 (C4 (Web Text))

Max Activating Token Index: 464