Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2354 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1204. Min Range: -1.1204

Max Act: 1.1204. Min Act: -0.0003

Data Index: 389978 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8133. Min Act: -0.0003

Data Index: 209235 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8243. Min Act: -0.0003

Data Index: 783429 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8057. Min Act: -0.0003

Data Index: 1271565 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8358. Min Act: -0.0003

Data Index: 33084 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7681. Min Act: -0.0003

Data Index: 362890 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7455. Min Act: -0.0003

Data Index: 530944 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7639. Min Act: -0.0003

Data Index: 444706 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7564. Min Act: -0.0003

Data Index: 886058 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7463. Min Act: -0.0003

Data Index: 69374 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7598. Min Act: -0.0003

Data Index: 942261 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7629. Min Act: -0.0003

Data Index: 679103 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7791. Min Act: -0.0003

Data Index: 509798 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7133. Min Act: -0.0003

Data Index: 734440 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.6992. Min Act: -0.0003

Data Index: 604444 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7394. Min Act: -0.0003

Data Index: 341827 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7451. Min Act: -0.0003

Data Index: 628299 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.6690. Min Act: -0.0003

Data Index: 1166359 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.6268. Min Act: -0.0003

Data Index: 894621 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7356. Min Act: -0.0003

Data Index: 544414 (C4 (Web Text))

Max Activating Token Index: 385