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

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

Neuron 2935 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2576. Min Range: -3.2576

Max Act: 3.2576. Min Act: -0.0001

Data Index: 684214 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 3.2576. Min Range: -3.2576

Max Act: 3.2052. Min Act: -0.0001

Data Index: 394853 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.2576. Min Range: -3.2576

Max Act: 3.1864. Min Act: -0.0001

Data Index: 1289653 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.9849. Min Act: -0.0001

Data Index: 1037283 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8327. Min Act: -0.0001

Data Index: 7943 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8910. Min Act: -0.0001

Data Index: 1243839 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7542. Min Act: -0.0001

Data Index: 151652 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7112. Min Act: -0.0001

Data Index: 544825 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.6741. Min Act: -0.0001

Data Index: 87976 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7314. Min Act: -0.0001

Data Index: 211607 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.4608. Min Act: -0.0001

Data Index: 613785 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.5573. Min Act: -0.0001

Data Index: 689218 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.3539. Min Act: -0.0001

Data Index: 1253656 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.5777. Min Act: -0.0001

Data Index: 862126 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.3979. Min Act: -0.0001

Data Index: 1069487 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.3865. Min Act: -0.0001

Data Index: 620244 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.3477. Min Act: -0.0001

Data Index: 206481 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.1907. Min Act: -0.0001

Data Index: 98227 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.3093. Min Act: -0.0001

Data Index: 259485 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.2230. Min Act: -0.0001

Data Index: 1129792 (C4 (Web Text))

Max Activating Token Index: 104