Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 761 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.1406. Min Act: -0.0000

Data Index: 650040 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.1452. Min Act: -0.0000

Data Index: 886502 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.0099. Min Act: -0.0000

Data Index: 632365 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.1452. Min Range: -2.1452

Max Act: 2.1258. Min Act: -0.0000

Data Index: 104384 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9865. Min Act: -0.0000

Data Index: 697480 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.8598. Min Act: -0.0000

Data Index: 955826 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9128. Min Act: -0.0000

Data Index: 80219 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9972. Min Act: -0.0000

Data Index: 735359 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6756. Min Act: -0.0000

Data Index: 324303 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9515. Min Act: -0.0000

Data Index: 1228233 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.9141. Min Act: -0.0000

Data Index: 1051026 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.7841. Min Act: -0.0000

Data Index: 43832 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6945. Min Act: -0.0000

Data Index: 381594 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6165. Min Act: -0.0000

Data Index: 919033 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.7256. Min Act: -0.0000

Data Index: 896377 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.5935. Min Act: -0.0000

Data Index: 886044 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1595672 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.5472. Min Act: -0.0000

Data Index: 69022 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.5798. Min Act: -0.0000

Data Index: 1097394 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 2.1452. Min Range: -2.1452

Max Act: 1.7587. Min Act: -0.0000

Data Index: 284125 (C4 (Web Text))

Max Activating Token Index: 535