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

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

Neuron 2562 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9924. Min Act: -0.0001

Data Index: 646443 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1151374 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 1.0384. Min Range: -1.0384

Max Act: 1.0384. Min Act: -0.0001

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1032538 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9094. Min Act: -0.0001

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.9002. Min Act: -0.0000

Data Index: 861307 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8274. Min Act: -0.0001

Data Index: 989699 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8412. Min Act: -0.0000

Data Index: 22967 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8225. Min Act: -0.0001

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8691. Min Act: -0.0001

Data Index: 350546 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8275. Min Act: -0.0001

Data Index: 28765 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8024. Min Act: -0.0000

Data Index: 662544 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1279670 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.8026. Min Act: -0.0001

Data Index: 261127 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7951. Min Act: -0.0001

Data Index: 32651 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7990. Min Act: -0.0000

Data Index: 326906 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7411. Min Act: -0.0001

Data Index: 562710 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7184. Min Act: -0.0001

Data Index: 512968 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7556. Min Act: -0.0001

Data Index: 387716 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 1.0384. Min Range: -1.0384

Max Act: 0.7688. Min Act: -0.0001

Data Index: 1060162 (C4 (Web Text))

Max Activating Token Index: 272