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

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

Neuron 4959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6473. Min Range: -4.6473

Max Act: 4.6473. Min Act: -0.0000

Data Index: 478662 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.9542. Min Act: -0.0000

Data Index: 582809 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.9181. Min Act: -0.0000

Data Index: 906723 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.7345. Min Act: -0.0000

Data Index: 1265747 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 4.6473. Min Range: -4.6473

Max Act: 4.2351. Min Act: -0.0000

Data Index: 70950 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.9470. Min Act: -0.0000

Data Index: 284637 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.9026. Min Act: -0.0000

Data Index: 1145447 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.6426. Min Act: -0.0000

Data Index: 771698 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.5977. Min Act: -0.0000

Data Index: 1091079 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.5664. Min Act: -0.0000

Data Index: 71989 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.3889. Min Act: -0.0000

Data Index: 1345787 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.7154. Min Act: -0.0000

Data Index: 502883 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.3782. Min Act: -0.0000

Data Index: 1074452 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.4936. Min Act: -0.0000

Data Index: 1288787 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.4909. Min Act: -0.0000

Data Index: 821163 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.4981. Min Act: -0.0000

Data Index: 208127 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.2798. Min Act: -0.0000

Data Index: 911692 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.4050. Min Act: -0.0000

Data Index: 591633 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.5502. Min Act: -0.0000

Data Index: 633886 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 4.6473. Min Range: -4.6473

Max Act: 3.3774. Min Act: -0.0000

Data Index: 456316 (C4 (Web Text))

Max Activating Token Index: 630