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

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

Neuron 2940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4847. Min Act: -0.0001

Data Index: 337914 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4212. Min Act: -0.0001

Data Index: 190872 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4029. Min Act: -0.0001

Data Index: 712260 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3706. Min Act: -0.0000

Data Index: 606171 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3452. Min Act: -0.0001

Data Index: 728298 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3102. Min Act: -0.0001

Data Index: 240419 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2961. Min Act: -0.0001

Data Index: 849971 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3204. Min Act: -0.0000

Data Index: 3526 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1356804 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3090. Min Act: -0.0001

Data Index: 441668 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3061. Min Act: -0.0001

Data Index: 996863 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2891. Min Act: -0.0000

Data Index: 902015 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2776. Min Act: -0.0001

Data Index: 685470 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2740. Min Act: -0.0001

Data Index: 657633 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2686. Min Act: -0.0000

Data Index: 385036 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1003837 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2870. Min Act: -0.0001

Data Index: 1004364 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1290659 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2606. Min Act: -0.0001

Data Index: 1172916 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2786. Min Act: -0.0001

Data Index: 155163 (C4 (Web Text))

Max Activating Token Index: 934