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

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

Neuron 3823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2212. Min Range: -2.2212

Max Act: 2.2088. Min Act: -0.0000

Data Index: 941471 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 2.2212. Min Range: -2.2212

Max Act: 2.2114. Min Act: -0.0000

Data Index: 938928 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 2.2212. Min Range: -2.2212

Max Act: 2.2212. Min Act: -0.0000

Data Index: 329637 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 2.2212. Min Range: -2.2212

Max Act: 2.0779. Min Act: -0.0000

Data Index: 809 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 2.2212. Min Range: -2.2212

Max Act: 2.0046. Min Act: -0.0000

Data Index: 1355278 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.6634. Min Act: -0.0000

Data Index: 420859 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.6544. Min Act: -0.0000

Data Index: 659181 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.7184. Min Act: -0.0000

Data Index: 997703 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.6410. Min Act: -0.0000

Data Index: 257470 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1016822 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.6652. Min Act: -0.0000

Data Index: 385743 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.7659. Min Act: -0.0000

Data Index: 598173 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1236834 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.5571. Min Act: -0.0000

Data Index: 714036 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 2.2212. Min Range: -2.2212

Max Act: 2.1674. Min Act: -0.0000

Data Index: 525334 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.4902. Min Act: -0.0000

Data Index: 439424 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.7103. Min Act: -0.0000

Data Index: 506784 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.6021. Min Act: -0.0000

Data Index: 603943 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.7100. Min Act: -0.0000

Data Index: 634288 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 2.2212. Min Range: -2.2212

Max Act: 1.5037. Min Act: -0.0000

Data Index: 400018 (C4 (Web Text))

Max Activating Token Index: 154