Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4435 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.3475. Min Act: -0.0001

Data Index: 1250758 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1472. Min Act: -0.0001

Data Index: 1092952 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0248. Min Act: -0.0001

Data Index: 703722 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.1820. Min Act: -0.0001

Data Index: 675388 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0038. Min Act: -0.0001

Data Index: 647508 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0650. Min Act: -0.0001

Data Index: 120087 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 1.3475. Min Range: -1.3475

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1114337 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.8744. Min Act: -0.0001

Data Index: 398573 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.9275. Min Act: -0.0001

Data Index: 1017184 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.9480. Min Act: -0.0001

Data Index: 857117 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.8479. Min Act: -0.0001

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.9401. Min Act: -0.0001

Data Index: 238554 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.9147. Min Act: -0.0001

Data Index: 348999 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.8902. Min Act: -0.0001

Data Index: 1090366 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1314882 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.8715. Min Act: -0.0001

Data Index: 397682 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.8449. Min Act: -0.0001

Data Index: 217546 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.7864. Min Act: -0.0001

Data Index: 1018732 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.8138. Min Act: -0.0001

Data Index: 711121 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.3475. Min Range: -1.3475

Max Act: 0.8596. Min Act: -0.0001

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 741