Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4896 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.4032. Min Act: -0.0000

Data Index: 443174 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.7866. Min Act: -0.0000

Data Index: 918441 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.2970. Min Act: -0.0000

Data Index: 746523 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.3023. Min Act: -0.0000

Data Index: 184339 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.1081. Min Act: -0.0000

Data Index: 1323256 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.9699. Min Act: -0.0000

Data Index: 255095 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.0637. Min Act: -0.0000

Data Index: 317755 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.1299. Min Act: -0.0000

Data Index: 378978 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 2.7866. Min Range: -2.7866

Max Act: 2.0191. Min Act: -0.0000

Data Index: 213533 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.9996. Min Act: -0.0000

Data Index: 967993 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.9419. Min Act: -0.0000

Data Index: 902166 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.6477. Min Act: -0.0000

Data Index: 896531 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.9076. Min Act: -0.0000

Data Index: 501464 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.6197. Min Act: -0.0000

Data Index: 403521 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.7718. Min Act: -0.0000

Data Index: 580520 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.8591. Min Act: -0.0000

Data Index: 319233 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.8599. Min Act: -0.0000

Data Index: 546428 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.9488. Min Act: -0.0000

Data Index: 346940 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.9356. Min Act: -0.0000

Data Index: 1059154 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 2.7866. Min Range: -2.7866

Max Act: 1.8181. Min Act: -0.0000

Data Index: 922941 (C4 (Web Text))

Max Activating Token Index: 759