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

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

Neuron 81 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: 3.4853. Min Range: -3.4853

Max Act: 3.3613. Min Act: -0.0001

Data Index: 827925 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 3.4853. Min Range: -3.4853

Max Act: 3.4853. Min Act: -0.0001

Data Index: 889265 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 3.4853. Min Range: -3.4853

Max Act: 3.0044. Min Act: -0.0001

Data Index: 880365 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 3.4853. Min Range: -3.4853

Max Act: 3.0279. Min Act: -0.0001

Data Index: 52141 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.6525. Min Act: -0.0001

Data Index: 952353 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 3.4853. Min Range: -3.4853

Max Act: 3.0069. Min Act: -0.0001

Data Index: 343803 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.8420. Min Act: -0.0000

Data Index: 1204995 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.6560. Min Act: -0.0001

Data Index: 1286931 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.9623. Min Act: -0.0001

Data Index: 1029697 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.5212. Min Act: -0.0000

Data Index: 51896 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.7060. Min Act: -0.0001

Data Index: 916795 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.6949. Min Act: -0.0001

Data Index: 413123 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.6864. Min Act: -0.0001

Data Index: 476151 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.5192. Min Act: -0.0000

Data Index: 1072792 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.7194. Min Act: -0.0001

Data Index: 756282 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.6835. Min Act: -0.0001

Data Index: 368922 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.5257. Min Act: -0.0001

Data Index: 710648 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.3450. Min Act: -0.0001

Data Index: 586762 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.4642. Min Act: -0.0001

Data Index: 657 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 3.4853. Min Range: -3.4853

Max Act: 2.4806. Min Act: -0.0001

Data Index: 706092 (C4 (Web Text))

Max Activating Token Index: 722