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

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

Neuron 3120 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8906. Min Range: -4.8906

Max Act: 4.8906. Min Act: -0.0000

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 4.8906. Min Range: -4.8906

Max Act: 3.6632. Min Act: -0.0000

Data Index: 192818 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 4.8906. Min Range: -4.8906

Max Act: 3.5156. Min Act: -0.0000

Data Index: 1146136 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 4.8906. Min Range: -4.8906

Max Act: 3.4122. Min Act: -0.0000

Data Index: 280057 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 4.8906. Min Range: -4.8906

Max Act: 3.0748. Min Act: -0.0000

Data Index: 521946 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 4.8906. Min Range: -4.8906

Max Act: 3.2263. Min Act: -0.0000

Data Index: 65056 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.8281. Min Act: -0.0000

Data Index: 782945 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.9048. Min Act: -0.0000

Data Index: 1271587 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.6369. Min Act: -0.0000

Data Index: 491419 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.7552. Min Act: -0.0000

Data Index: 1206754 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.4238. Min Act: 0.0000

Data Index: 1095876 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.6389. Min Act: -0.0000

Data Index: 1048192 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.4261. Min Act: -0.0000

Data Index: 618986 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.2816. Min Act: -0.0000

Data Index: 1347234 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.2061. Min Act: -0.0000

Data Index: 527860 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.1268. Min Act: -0.0000

Data Index: 135726 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 4.8906. Min Range: -4.8906

Max Act: 3.7730. Min Act: -0.0000

Data Index: 365165 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.3216. Min Act: 0.0000

Data Index: 980578 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.2725. Min Act: -0.0000

Data Index: 1342845 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 4.8906. Min Range: -4.8906

Max Act: 2.2575. Min Act: -0.0000

Data Index: 769651 (C4 (Web Text))

Max Activating Token Index: 92