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

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

Neuron 3621 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3821. Min Range: -3.3821

Max Act: 3.3821. Min Act: -0.0001

Data Index: 1184169 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 3.3821. Min Range: -3.3821

Max Act: 3.3319. Min Act: -0.0001

Data Index: 967200 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 3.3821. Min Range: -3.3821

Max Act: 3.2101. Min Act: -0.0001

Data Index: 1237677 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.3821. Min Range: -3.3821

Max Act: 3.0467. Min Act: -0.0001

Data Index: 1152703 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.8812. Min Act: -0.0001

Data Index: 1519 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.7537. Min Act: -0.0001

Data Index: 484824 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.6817. Min Act: -0.0001

Data Index: 1253926 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.8109. Min Act: -0.0001

Data Index: 932301 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.9158. Min Act: -0.0001

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.6418. Min Act: -0.0001

Data Index: 1258644 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.6574. Min Act: -0.0001

Data Index: 1349871 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.9117. Min Act: -0.0001

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.7646. Min Act: -0.0001

Data Index: 1041431 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.7131. Min Act: -0.0001

Data Index: 1040615 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.5811. Min Act: -0.0001

Data Index: 686743 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.7884. Min Act: -0.0001

Data Index: 907421 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.5278. Min Act: -0.0001

Data Index: 466120 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.6387. Min Act: -0.0001

Data Index: 265309 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.6115. Min Act: -0.0001

Data Index: 1278448 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.3821. Min Range: -3.3821

Max Act: 2.3862. Min Act: -0.0001

Data Index: 944430 (C4 (Web Text))

Max Activating Token Index: 645