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

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

Neuron 3441 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3523. Min Act: -0.0001

Data Index: 444457 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1306093 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3482. Min Act: -0.0001

Data Index: 761238 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1209255 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3293. Min Act: -0.0001

Data Index: 637632 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3238. Min Act: -0.0001

Data Index: 31248 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3181. Min Act: -0.0001

Data Index: 27571 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2781. Min Act: -0.0001

Data Index: 875273 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3376. Min Act: -0.0001

Data Index: 449011 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3043. Min Act: -0.0001

Data Index: 1057126 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3112. Min Act: -0.0001

Data Index: 231714 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3116. Min Act: -0.0001

Data Index: 984022 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.3074. Min Act: -0.0001

Data Index: 345884 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2912. Min Act: -0.0001

Data Index: 551829 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2791. Min Act: -0.0001

Data Index: 514724 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2714. Min Act: -0.0001

Data Index: 717171 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2939. Min Act: -0.0001

Data Index: 968017 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2849. Min Act: -0.0001

Data Index: 420789 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2583. Min Act: -0.0001

Data Index: 115609 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.3615. Min Range: -0.3615

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1054450 (C4 (Web Text))

Max Activating Token Index: 412