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

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

Neuron 3684 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0103. Min Range: -1.0103

Max Act: 1.0103. Min Act: -0.0001

Data Index: 1175405 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9677. Min Act: -0.0002

Data Index: 215307 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9428. Min Act: -0.0002

Data Index: 678823 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8826. Min Act: -0.0002

Data Index: 777140 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9428. Min Act: -0.0001

Data Index: 802540 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8463. Min Act: -0.0001

Data Index: 874080 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8712. Min Act: -0.0001

Data Index: 32850 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8534. Min Act: -0.0002

Data Index: 96339 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8004. Min Act: -0.0001

Data Index: 631250 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8197. Min Act: -0.0002

Data Index: 967212 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8288. Min Act: -0.0001

Data Index: 47829 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7917. Min Act: -0.0002

Data Index: 1332308 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7313. Min Act: -0.0002

Data Index: 1212109 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7196. Min Act: -0.0001

Data Index: 661387 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9260. Min Act: -0.0002

Data Index: 397157 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8194. Min Act: -0.0001

Data Index: 799644 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7776. Min Act: -0.0001

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7349. Min Act: -0.0002

Data Index: 1206632 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7651. Min Act: -0.0002

Data Index: 542531 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.7748. Min Act: -0.0002

Data Index: 516107 (C4 (Web Text))

Max Activating Token Index: 780