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

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

Neuron 1842 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: 3.2941. Min Range: -3.2941

Max Act: 3.2941. Min Act: -0.0000

Data Index: 1186498 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.6168. Min Act: 0.0000

Data Index: 842661 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.3363. Min Act: 0.0000

Data Index: 779032 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.3482. Min Act: -0.0001

Data Index: 361133 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.2137. Min Act: 0.0000

Data Index: 261589 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.3223. Min Act: 0.0000

Data Index: 1234026 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.0919. Min Act: -0.0000

Data Index: 861127 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.9642. Min Act: 0.0001

Data Index: 528808 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.0809. Min Act: 0.0000

Data Index: 610573 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.0379. Min Act: 0.0001

Data Index: 98247 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.2024. Min Act: 0.0000

Data Index: 422356 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.5119. Min Act: 0.0000

Data Index: 384834 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.9900. Min Act: -0.0000

Data Index: 1213545 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.9700. Min Act: -0.0000

Data Index: 129792 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 3.2941. Min Range: -3.2941

Max Act: 2.0364. Min Act: -0.0000

Data Index: 1347903 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.7618. Min Act: 0.0000

Data Index: 241291 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.6864. Min Act: 0.0000

Data Index: 1089690 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.8107. Min Act: -0.0001

Data Index: 89265 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.7314. Min Act: 0.0000

Data Index: 912574 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.2941. Min Range: -3.2941

Max Act: 1.9281. Min Act: -0.0000

Data Index: 691628 (C4 (Web Text))

Max Activating Token Index: 152