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

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

Neuron 142 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: 1.2059. Min Range: -1.2059

Max Act: 1.2059. Min Act: -0.0001

Data Index: 799640 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.0356. Min Act: -0.0001

Data Index: 1173163 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.1262. Min Act: -0.0001

Data Index: 759882 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.0147. Min Act: -0.0001

Data Index: 301212 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.0114. Min Act: -0.0001

Data Index: 360731 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.0073. Min Act: -0.0001

Data Index: 482834 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.0452. Min Act: -0.0001

Data Index: 383801 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9494. Min Act: -0.0001

Data Index: 498545 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9513. Min Act: -0.0001

Data Index: 957185 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.0032. Min Act: -0.0001

Data Index: 1289210 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9461. Min Act: -0.0001

Data Index: 42296 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.8069. Min Act: -0.0001

Data Index: 1216461 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9638. Min Act: -0.0001

Data Index: 219132 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7927. Min Act: -0.0001

Data Index: 190002 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9073. Min Act: -0.0001

Data Index: 985653 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9956. Min Act: -0.0001

Data Index: 635969 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.2059. Min Range: -1.2059

Max Act: 1.0020. Min Act: -0.0001

Data Index: 666077 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9258. Min Act: -0.0001

Data Index: 194279 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.7949. Min Act: -0.0001

Data Index: 566353 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.2059. Min Range: -1.2059

Max Act: 0.9705. Min Act: -0.0001

Data Index: 776371 (C4 (Web Text))

Max Activating Token Index: 368