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

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

Neuron 1070 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: 1.0497. Min Range: -1.0497

Max Act: 1.0497. Min Act: -0.0001

Data Index: 446799 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.9339. Min Act: -0.0001

Data Index: 1062886 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.9150. Min Act: -0.0001

Data Index: 782060 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.8583. Min Act: -0.0001

Data Index: 266988 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.8315. Min Act: -0.0001

Data Index: 358732 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7849. Min Act: -0.0001

Data Index: 889995 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7997. Min Act: -0.0001

Data Index: 937302 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7762. Min Act: -0.0001

Data Index: 1268911 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7268. Min Act: -0.0001

Data Index: 688017 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.8013. Min Act: -0.0001

Data Index: 1244999 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7983. Min Act: -0.0001

Data Index: 1095366 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.8144. Min Act: -0.0001

Data Index: 145571 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7462. Min Act: -0.0001

Data Index: 251643 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1119385 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7269. Min Act: -0.0001

Data Index: 847698 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7452. Min Act: -0.0001

Data Index: 814478 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7652. Min Act: -0.0001

Data Index: 312749 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.6865. Min Act: -0.0001

Data Index: 347577 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7120. Min Act: -0.0001

Data Index: 964734 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 1.0497. Min Range: -1.0497

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1046176 (C4 (Web Text))

Max Activating Token Index: 853