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

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

Neuron 3252 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: 2.5965. Min Range: -2.5965

Max Act: 2.5965. Min Act: -0.0000

Data Index: 223912 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.3245. Min Act: -0.0000

Data Index: 759873 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.4309. Min Act: -0.0000

Data Index: 9869 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.4220. Min Act: -0.0000

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.1713. Min Act: -0.0000

Data Index: 1133541 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.3953. Min Act: -0.0000

Data Index: 660073 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.4976. Min Act: -0.0000

Data Index: 1313430 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.3723. Min Act: -0.0000

Data Index: 223414 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.3431. Min Act: -0.0000

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.3287. Min Act: -0.0000

Data Index: 1267361 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.4515. Min Act: -0.0000

Data Index: 966934 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.3271. Min Act: -0.0000

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.4262. Min Act: -0.0000

Data Index: 397667 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.2923. Min Act: -0.0000

Data Index: 65266 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.2673. Min Act: -0.0000

Data Index: 1323698 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.3534. Min Act: -0.0000

Data Index: 565444 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.1396. Min Act: -0.0000

Data Index: 1045089 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.2346. Min Act: -0.0000

Data Index: 827910 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.2040. Min Act: -0.0000

Data Index: 134340 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 2.5965. Min Range: -2.5965

Max Act: 2.2059. Min Act: -0.0000

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 818