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

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

Neuron 3600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3878. Min Act: -0.0000

Data Index: 178766 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.4019. Min Act: -0.0000

Data Index: 916685 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3634. Min Act: -0.0000

Data Index: 76054 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3665. Min Act: -0.0000

Data Index: 640562 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3403. Min Act: -0.0001

Data Index: 315803 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3150. Min Act: -0.0000

Data Index: 362014 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3057. Min Act: -0.0001

Data Index: 225698 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3060. Min Act: -0.0000

Data Index: 646163 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3017. Min Act: -0.0000

Data Index: 260855 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3180. Min Act: -0.0001

Data Index: 298430 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3166. Min Act: -0.0000

Data Index: 134427 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3212. Min Act: -0.0001

Data Index: 65230 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1295429 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3309. Min Act: -0.0000

Data Index: 631732 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2812. Min Act: -0.0000

Data Index: 589202 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1356143 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1034958 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1036841 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2538. Min Act: -0.0001

Data Index: 463053 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2628. Min Act: -0.0001

Data Index: 193222 (C4 (Web Text))

Max Activating Token Index: 446