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

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

Neuron 2058 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1234. Min Range: -3.1234

Max Act: 3.1234. Min Act: -0.0001

Data Index: 420231 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.7683. Min Act: -0.0001

Data Index: 793601 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.3921. Min Act: -0.0001

Data Index: 239384 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.1911. Min Act: -0.0001

Data Index: 18356 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.3612. Min Act: -0.0001

Data Index: 1241974 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.2826. Min Act: -0.0001

Data Index: 1318287 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.0500. Min Act: -0.0001

Data Index: 298495 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.1920. Min Act: -0.0001

Data Index: 599499 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.0539. Min Act: -0.0001

Data Index: 297646 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.0182. Min Act: -0.0001

Data Index: 578699 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.1234. Min Range: -3.1234

Max Act: 1.9430. Min Act: -0.0001

Data Index: 170234 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.0044. Min Act: -0.0001

Data Index: 955409 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.0598. Min Act: -0.0001

Data Index: 482676 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 3.1234. Min Range: -3.1234

Max Act: 2.0020. Min Act: -0.0001

Data Index: 731119 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 3.1234. Min Range: -3.1234

Max Act: 1.9318. Min Act: -0.0001

Data Index: 739984 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 3.1234. Min Range: -3.1234

Max Act: 1.7089. Min Act: -0.0001

Data Index: 1001401 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.1234. Min Range: -3.1234

Max Act: 1.8700. Min Act: -0.0001

Data Index: 233600 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 3.1234. Min Range: -3.1234

Max Act: 1.8781. Min Act: -0.0001

Data Index: 1349347 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 3.1234. Min Range: -3.1234

Max Act: 1.7201. Min Act: -0.0001

Data Index: 396839 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 3.1234. Min Range: -3.1234

Max Act: 1.8068. Min Act: -0.0001

Data Index: 135946 (C4 (Web Text))

Max Activating Token Index: 196