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

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

Neuron 5116 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: 0.8245. Min Range: -0.8245

Max Act: 0.8245. Min Act: -0.0000

Data Index: 337188 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.7215. Min Act: -0.0000

Data Index: 104278 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6824. Min Act: -0.0000

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.6084. Min Act: -0.0000

Data Index: 377938 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1020597 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5181. Min Act: -0.0000

Data Index: 242215 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.5102. Min Act: -0.0000

Data Index: 964902 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4904. Min Act: -0.0000

Data Index: 179919 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1171763 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4421. Min Act: -0.0000

Data Index: 623468 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1197312 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1095130 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4215. Min Act: -0.0000

Data Index: 404534 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4305. Min Act: -0.0000

Data Index: 895960 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4400. Min Act: -0.0000

Data Index: 90712 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1134576 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4085. Min Act: -0.0000

Data Index: 145896 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1247156 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1247707 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.8245. Min Range: -0.8245

Max Act: 0.4350. Min Act: -0.0000

Data Index: 4572 (C4 (Web Text))

Max Activating Token Index: 639