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

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

Neuron 2257 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1156910 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1532198 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1102192 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1056592 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1505501 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1274. Min Act: -0.0000

Data Index: 197321 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1227. Min Act: -0.0000

Data Index: 860347 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1603160 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1181. Min Act: -0.0000

Data Index: 168329 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1210. Min Act: -0.0000

Data Index: 231106 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1181. Min Act: -0.0000

Data Index: 200103 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1013128 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1166. Min Act: -0.0000

Data Index: 720680 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1148. Min Act: -0.0000

Data Index: 617003 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1150316 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1641509 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1108. Min Act: -0.0000

Data Index: 772412 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1184102 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1301049 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.1887. Min Range: -0.1887

Max Act: 0.1029. Min Act: -0.0000

Data Index: 85373 (C4 (Web Text))

Max Activating Token Index: 523