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

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

Neuron 1733 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7606. Min Act: -0.0002

Data Index: 1210008 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1378377 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.6577. Min Act: -0.0001

Data Index: 730959 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5772. Min Act: -0.0002

Data Index: 1007088 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5646. Min Act: -0.0001

Data Index: 1624986 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5706. Min Act: -0.0001

Data Index: 118442 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5634. Min Act: -0.0002

Data Index: 1031288 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5134. Min Act: -0.0002

Data Index: 221306 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5553. Min Act: -0.0002

Data Index: 1357816 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1538191 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5424. Min Act: -0.0001

Data Index: 263629 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5418. Min Act: -0.0001

Data Index: 1650767 (Python Code)

Max Activating Token Index: 476

Text #12

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5150. Min Act: -0.0001

Data Index: 1554449 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5067. Min Act: -0.0001

Data Index: 1445965 (Python Code)

Max Activating Token Index: 566

Text #14

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5251. Min Act: -0.0001

Data Index: 1370053 (Python Code)

Max Activating Token Index: 513

Text #15

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5073. Min Act: -0.0002

Data Index: 770630 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.4885. Min Act: -0.0001

Data Index: 1521438 (Python Code)

Max Activating Token Index: 745

Text #17

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5362. Min Act: -0.0001

Data Index: 1522354 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1535707 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 0.7820. Min Range: -0.7820

Max Act: 0.4698. Min Act: -0.0002

Data Index: 1024627 (C4 (Web Text))

Max Activating Token Index: 63