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

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

Neuron 2321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.4767. Min Act: -0.0000

Data Index: 152965 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.1530. Min Act: -0.0000

Data Index: 791198 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.0521. Min Act: -0.0000

Data Index: 737737 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9708. Min Act: -0.0000

Data Index: 29710 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1178099 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9338. Min Act: -0.0000

Data Index: 376965 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.4767. Min Range: -1.4767

Max Act: 1.0680. Min Act: -0.0000

Data Index: 873871 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1170510 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9882. Min Act: -0.0000

Data Index: 507590 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.8910. Min Act: -0.0000

Data Index: 170541 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1327395 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.7555. Min Act: -0.0000

Data Index: 400570 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.8857. Min Act: -0.0001

Data Index: 330628 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9405. Min Act: -0.0000

Data Index: 520203 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.8605. Min Act: -0.0000

Data Index: 754716 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1259104 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.8553. Min Act: -0.0000

Data Index: 638182 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.8715. Min Act: -0.0000

Data Index: 763046 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.8709. Min Act: -0.0000

Data Index: 698227 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.4767. Min Range: -1.4767

Max Act: 0.9076. Min Act: -0.0000

Data Index: 817053 (C4 (Web Text))

Max Activating Token Index: 603