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

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

Neuron 664 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1231. Min Range: -1.1231

Max Act: 1.1231. Min Act: -0.0001

Data Index: 1340318 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9855. Min Act: -0.0001

Data Index: 244167 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.1231. Min Range: -1.1231

Max Act: 1.0367. Min Act: -0.0001

Data Index: 744436 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9453. Min Act: -0.0000

Data Index: 468778 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 1.1231. Min Range: -1.1231

Max Act: 1.0070. Min Act: -0.0001

Data Index: 935811 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9625. Min Act: -0.0001

Data Index: 249121 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9293. Min Act: -0.0000

Data Index: 722417 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9198. Min Act: -0.0001

Data Index: 517794 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9482. Min Act: -0.0001

Data Index: 1584058 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9305. Min Act: -0.0001

Data Index: 494287 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.9009. Min Act: -0.0001

Data Index: 732301 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.8852. Min Act: -0.0001

Data Index: 914034 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.8839. Min Act: -0.0001

Data Index: 382172 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.8976. Min Act: -0.0001

Data Index: 1123988 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.8339. Min Act: -0.0001

Data Index: 1329555 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.8221. Min Act: -0.0001

Data Index: 1126051 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.7696. Min Act: -0.0001

Data Index: 564516 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.8417. Min Act: -0.0001

Data Index: 758819 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.8347. Min Act: -0.0001

Data Index: 1001314 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.1231. Min Range: -1.1231

Max Act: 0.7456. Min Act: -0.0001

Data Index: 194825 (C4 (Web Text))

Max Activating Token Index: 973