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

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

Neuron 2005 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.9319. Min Act: -0.0000

Data Index: 235757 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8671. Min Act: -0.0000

Data Index: 508019 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8188. Min Act: -0.0000

Data Index: 309957 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8220. Min Act: -0.0000

Data Index: 470065 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7350. Min Act: -0.0000

Data Index: 114564 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8301. Min Act: -0.0000

Data Index: 263066 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.8239. Min Act: -0.0000

Data Index: 345667 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1309939 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7789. Min Act: -0.0000

Data Index: 470394 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7144. Min Act: -0.0000

Data Index: 370729 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7423. Min Act: -0.0000

Data Index: 890787 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7771. Min Act: -0.0000

Data Index: 25013 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6957. Min Act: -0.0000

Data Index: 162357 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7060. Min Act: -0.0000

Data Index: 12324 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7578. Min Act: -0.0000

Data Index: 357067 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1222745 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1328153 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1307841 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.7408. Min Act: -0.0000

Data Index: 324284 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.9319. Min Range: -0.9319

Max Act: 0.6884. Min Act: -0.0000

Data Index: 371074 (C4 (Web Text))

Max Activating Token Index: 170