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

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

Neuron 3866 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8987. Min Range: -2.8987

Max Act: 2.8987. Min Act: -0.0000

Data Index: 192087 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 2.8987. Min Range: -2.8987

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1336860 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 2.8987. Min Range: -2.8987

Max Act: 2.5415. Min Act: -0.0000

Data Index: 186650 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.7360. Min Act: -0.0000

Data Index: 958482 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.8768. Min Act: -0.0000

Data Index: 51375 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.7887. Min Act: -0.0000

Data Index: 618639 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.6403. Min Act: -0.0000

Data Index: 1584994 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.6008. Min Act: -0.0000

Data Index: 1061353 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.4254. Min Act: -0.0000

Data Index: 39770 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.4749. Min Act: -0.0000

Data Index: 549064 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.5027. Min Act: -0.0000

Data Index: 122219 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.5248. Min Act: -0.0000

Data Index: 247367 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.5564. Min Act: -0.0000

Data Index: 336304 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.3927. Min Act: -0.0000

Data Index: 333149 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.4461. Min Act: -0.0000

Data Index: 1258180 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.5052. Min Act: -0.0000

Data Index: 40771 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1133272 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.3874. Min Act: -0.0000

Data Index: 672493 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.5003. Min Act: -0.0000

Data Index: 480840 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 2.8987. Min Range: -2.8987

Max Act: 1.2136. Min Act: -0.0000

Data Index: 858081 (C4 (Web Text))

Max Activating Token Index: 77