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

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

Neuron 4150 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.9104. Min Act: -0.0000

Data Index: 657816 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.5214. Min Act: -0.0000

Data Index: 1150247 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.7027. Min Act: -0.0000

Data Index: 223956 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.4948. Min Act: -0.0000

Data Index: 662743 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.3372. Min Act: -0.0000

Data Index: 911507 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.2552. Min Act: -0.0000

Data Index: 921610 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.6869. Min Act: -0.0000

Data Index: 604579 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.9585. Min Act: -0.0000

Data Index: 219158 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.9222. Min Act: -0.0000

Data Index: 892650 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.9425. Min Act: -0.0000

Data Index: 203983 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.8983. Min Act: -0.0000

Data Index: 1340133 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.7474. Min Act: -0.0000

Data Index: 1141596 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 3.9104. Min Range: -3.9104

Max Act: 3.0209. Min Act: -0.0000

Data Index: 1356024 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.8402. Min Act: -0.0000

Data Index: 9125 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.9215. Min Act: -0.0000

Data Index: 337212 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.7595. Min Act: -0.0000

Data Index: 1278323 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.7519. Min Act: -0.0000

Data Index: 1350815 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.8450. Min Act: -0.0000

Data Index: 895478 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.7067. Min Act: -0.0000

Data Index: 1261091 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.9104. Min Range: -3.9104

Max Act: 2.6543. Min Act: -0.0000

Data Index: 471944 (C4 (Web Text))

Max Activating Token Index: 886