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

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

Neuron 3876 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3603. Min Act: -0.0001

Data Index: 256035 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2871. Min Act: -0.0001

Data Index: 209540 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3175. Min Act: -0.0001

Data Index: 766787 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2681. Min Act: -0.0001

Data Index: 620847 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1964. Min Act: -0.0001

Data Index: 718765 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2499. Min Act: -0.0001

Data Index: 250273 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1168. Min Act: -0.0001

Data Index: 412727 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1532. Min Act: -0.0001

Data Index: 1221512 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1814. Min Act: -0.0001

Data Index: 933320 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1424. Min Act: -0.0001

Data Index: 158810 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0008. Min Act: -0.0001

Data Index: 506657 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9980. Min Act: -0.0001

Data Index: 168439 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0301. Min Act: -0.0001

Data Index: 631969 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0273. Min Act: -0.0001

Data Index: 593758 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9158. Min Act: -0.0001

Data Index: 770711 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9438. Min Act: -0.0001

Data Index: 317900 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9408. Min Act: -0.0001

Data Index: 5843 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8903. Min Act: -0.0001

Data Index: 783331 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9038. Min Act: -0.0001

Data Index: 366519 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.6818. Min Act: -0.0001

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 572