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

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

Neuron 2443 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.6231. Min Act: -0.0000

Data Index: 314139 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.4749. Min Act: -0.0000

Data Index: 484964 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.5451. Min Act: -0.0000

Data Index: 731880 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.3333. Min Act: -0.0000

Data Index: 320410 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.1487. Min Act: -0.0000

Data Index: 1316470 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.1024. Min Act: -0.0000

Data Index: 762734 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.0232. Min Act: -0.0000

Data Index: 1054024 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.3035. Min Act: -0.0000

Data Index: 1078075 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.3079. Min Act: -0.0000

Data Index: 577598 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.2489. Min Act: -0.0000

Data Index: 763782 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.1091. Min Act: -0.0000

Data Index: 1064341 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.1733. Min Act: -0.0000

Data Index: 605456 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.0274. Min Act: -0.0000

Data Index: 837155 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.1255. Min Act: -0.0000

Data Index: 1067811 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 3.6231. Min Range: -3.6231

Max Act: 3.1179. Min Act: -0.0000

Data Index: 208716 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 3.6231. Min Range: -3.6231

Max Act: 2.9528. Min Act: -0.0000

Data Index: 917040 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 3.6231. Min Range: -3.6231

Max Act: 2.9740. Min Act: -0.0000

Data Index: 885974 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 3.6231. Min Range: -3.6231

Max Act: 2.9578. Min Act: -0.0000

Data Index: 204591 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 3.6231. Min Range: -3.6231

Max Act: 2.9281. Min Act: -0.0000

Data Index: 355486 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 3.6231. Min Range: -3.6231

Max Act: 2.8458. Min Act: -0.0000

Data Index: 814570 (C4 (Web Text))

Max Activating Token Index: 403