Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3413 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.5340. Min Act: -0.0001

Data Index: 628717 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4221. Min Act: -0.0001

Data Index: 405361 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4155. Min Act: -0.0001

Data Index: 550578 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4448. Min Act: -0.0001

Data Index: 727212 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1029573 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4337. Min Act: -0.0001

Data Index: 193313 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1336156 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3708. Min Act: -0.0001

Data Index: 412939 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.4033. Min Act: -0.0001

Data Index: 740790 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3681. Min Act: -0.0000

Data Index: 697314 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1018926 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3843. Min Act: -0.0001

Data Index: 153302 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3540. Min Act: -0.0001

Data Index: 107121 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3406. Min Act: -0.0001

Data Index: 495858 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3623. Min Act: -0.0000

Data Index: 236967 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3684. Min Act: -0.0000

Data Index: 169251 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3413. Min Act: -0.0000

Data Index: 289566 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3259. Min Act: -0.0001

Data Index: 134408 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3176. Min Act: -0.0001

Data Index: 948971 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.5340. Min Range: -0.5340

Max Act: 0.3244. Min Act: -0.0001

Data Index: 1080483 (C4 (Web Text))

Max Activating Token Index: 742