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

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

Neuron 4345 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4340. Min Act: -0.0000

Data Index: 28627 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.4061. Min Act: -0.0000

Data Index: 431101 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3948. Min Act: -0.0000

Data Index: 773947 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1034543 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3437. Min Act: -0.0000

Data Index: 9991 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3632. Min Act: -0.0000

Data Index: 689623 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3608. Min Act: -0.0000

Data Index: 624161 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3537. Min Act: -0.0000

Data Index: 135834 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3431. Min Act: 0.0000

Data Index: 272080 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1216192 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3404. Min Act: -0.0000

Data Index: 473017 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3520. Min Act: -0.0000

Data Index: 493197 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3378. Min Act: -0.0000

Data Index: 51673 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3242. Min Act: 0.0000

Data Index: 174880 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3223. Min Act: -0.0000

Data Index: 450362 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1227350 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3065. Min Act: -0.0000

Data Index: 744138 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3285. Min Act: -0.0000

Data Index: 944990 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3150. Min Act: -0.0000

Data Index: 311216 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.4340. Min Range: -0.4340

Max Act: 0.3141. Min Act: -0.0000

Data Index: 175479 (C4 (Web Text))

Max Activating Token Index: 977