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

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

Neuron 1547 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: 2.2143. Min Range: -2.2143

Max Act: 2.2143. Min Act: -0.0000

Data Index: 848658 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.9464. Min Act: -0.0000

Data Index: 157706 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.8246. Min Act: -0.0000

Data Index: 479357 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.7576. Min Act: -0.0000

Data Index: 1417804 (Python Code)

Max Activating Token Index: 170

Text #4

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.4383. Min Act: -0.0000

Data Index: 477606 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1326517 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.3457. Min Act: -0.0000

Data Index: 584803 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.3428. Min Act: -0.0000

Data Index: 565926 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.3584. Min Act: -0.0000

Data Index: 128073 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.3151. Min Act: -0.0000

Data Index: 50416 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.2022. Min Act: -0.0000

Data Index: 78200 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.3225. Min Act: -0.0000

Data Index: 1484598 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.2466. Min Act: -0.0000

Data Index: 239165 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.2983. Min Act: -0.0000

Data Index: 226713 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.2285. Min Act: -0.0000

Data Index: 321223 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.2202. Min Act: -0.0000

Data Index: 239814 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.2909. Min Act: -0.0000

Data Index: 975208 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1115860 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.1024. Min Act: -0.0000

Data Index: 311070 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 2.2143. Min Range: -2.2143

Max Act: 1.1394. Min Act: -0.0000

Data Index: 317404 (C4 (Web Text))

Max Activating Token Index: 767