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

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

Neuron 672 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: 3.9473. Min Range: -3.9473

Max Act: 3.9473. Min Act: -0.0000

Data Index: 1234192 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 3.9473. Min Range: -3.9473

Max Act: 2.8911. Min Act: -0.0000

Data Index: 45605 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.9473. Min Range: -3.9473

Max Act: 3.0177. Min Act: -0.0000

Data Index: 908975 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.9473. Min Range: -3.9473

Max Act: 2.2540. Min Act: -0.0000

Data Index: 762330 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.9077. Min Act: -0.0000

Data Index: 437253 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 3.9473. Min Range: -3.9473

Max Act: 2.0119. Min Act: -0.0000

Data Index: 1009112 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.8579. Min Act: -0.0000

Data Index: 241956 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1248025 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.9010. Min Act: -0.0000

Data Index: 335516 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7825. Min Act: -0.0000

Data Index: 641931 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7448. Min Act: -0.0000

Data Index: 88299 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1232159 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7608. Min Act: -0.0000

Data Index: 67053 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7443. Min Act: -0.0000

Data Index: 570085 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7496. Min Act: -0.0000

Data Index: 371450 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1118835 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7221. Min Act: -0.0000

Data Index: 949203 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.8160. Min Act: -0.0000

Data Index: 846249 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.6939. Min Act: -0.0000

Data Index: 950482 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 3.9473. Min Range: -3.9473

Max Act: 1.7861. Min Act: -0.0000

Data Index: 116435 (C4 (Web Text))

Max Activating Token Index: 725