Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.7310. Min Act: -0.0000

Data Index: 394757 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.5665. Min Act: -0.0001

Data Index: 994709 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.5714. Min Act: -0.0001

Data Index: 573040 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1040685 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.4561. Min Act: -0.0000

Data Index: 95751 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.4400. Min Act: -0.0001

Data Index: 1006933 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3936. Min Act: -0.0000

Data Index: 48141 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3301. Min Act: -0.0000

Data Index: 9201 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3341. Min Act: -0.0001

Data Index: 60170 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.6817. Min Act: -0.0001

Data Index: 1215016 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3414. Min Act: -0.0001

Data Index: 603924 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2464. Min Act: -0.0001

Data Index: 676159 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3497. Min Act: -0.0001

Data Index: 752143 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3130. Min Act: -0.0000

Data Index: 317861 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3513. Min Act: -0.0001

Data Index: 219066 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3060. Min Act: -0.0001

Data Index: 623786 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2589. Min Act: -0.0001

Data Index: 944321 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2365. Min Act: -0.0000

Data Index: 481591 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.3948. Min Act: -0.0001

Data Index: 207836 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.7310. Min Range: -1.7310

Max Act: 1.2909. Min Act: -0.0001

Data Index: 1081958 (C4 (Web Text))

Max Activating Token Index: 653