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

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

Neuron 4755 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: 0.8661. Min Range: -0.8661

Max Act: 0.8032. Min Act: -0.0000

Data Index: 52478 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.8661. Min Act: -0.0000

Data Index: 825663 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7683. Min Act: -0.0000

Data Index: 780383 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7949. Min Act: -0.0000

Data Index: 186834 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.7945. Min Act: -0.0000

Data Index: 901028 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1288660 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6745. Min Act: -0.0000

Data Index: 565209 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1199974 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.5832. Min Act: -0.0000

Data Index: 971996 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1015738 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6167. Min Act: -0.0000

Data Index: 545266 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1212489 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6426. Min Act: -0.0000

Data Index: 418719 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6112. Min Act: -0.0000

Data Index: 414188 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6400. Min Act: -0.0000

Data Index: 459303 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6274. Min Act: -0.0000

Data Index: 934087 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6261. Min Act: -0.0000

Data Index: 944303 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6264. Min Act: -0.0000

Data Index: 26088 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.6248. Min Act: -0.0000

Data Index: 625072 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.8661. Min Range: -0.8661

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1478292 (Python Code)

Max Activating Token Index: 434