Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 703 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1182362 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1001597 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6828. Min Act: -0.0000

Data Index: 860492 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6393. Min Act: -0.0000

Data Index: 274125 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5819. Min Act: -0.0000

Data Index: 865589 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6215. Min Act: -0.0000

Data Index: 663899 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5855. Min Act: -0.0000

Data Index: 384885 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5720. Min Act: -0.0000

Data Index: 349009 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5931. Min Act: -0.0000

Data Index: 742388 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4949. Min Act: -0.0000

Data Index: 949811 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5422. Min Act: -0.0000

Data Index: 555772 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4277. Min Act: -0.0000

Data Index: 140458 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1225055 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3906. Min Act: -0.0000

Data Index: 835000 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3832. Min Act: 0.0000

Data Index: 105724 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1102171 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3743. Min Act: -0.0000

Data Index: 22951 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1079195 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3475. Min Act: 0.0000

Data Index: 1083515 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.3570. Min Act: -0.0000

Data Index: 855460 (C4 (Web Text))

Max Activating Token Index: 568