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

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

Neuron 1440 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3325. Min Range: -1.3325

Max Act: 1.3325. Min Act: -0.0000

Data Index: 762274 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.9053. Min Act: -0.0000

Data Index: 408978 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.9290. Min Act: -0.0000

Data Index: 42948 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.8736. Min Act: -0.0000

Data Index: 465911 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7585. Min Act: -0.0000

Data Index: 648157 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7944. Min Act: -0.0000

Data Index: 462012 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1002787 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1242698 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7140. Min Act: -0.0000

Data Index: 864524 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6666. Min Act: -0.0000

Data Index: 147710 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1101646 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1081864 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7521. Min Act: -0.0000

Data Index: 824745 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6817. Min Act: -0.0000

Data Index: 259241 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6997. Min Act: -0.0000

Data Index: 376280 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6957. Min Act: -0.0000

Data Index: 529463 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1314275 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6832. Min Act: -0.0000

Data Index: 387612 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7347. Min Act: -0.0000

Data Index: 913573 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1272966 (C4 (Web Text))

Max Activating Token Index: 239