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

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

Neuron 398 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: 4.5894. Min Range: -4.5894

Max Act: 4.5894. Min Act: -0.0000

Data Index: 944055 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 4.5894. Min Range: -4.5894

Max Act: 4.4031. Min Act: -0.0000

Data Index: 1183161 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.7610. Min Act: -0.0000

Data Index: 1175796 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.7495. Min Act: -0.0000

Data Index: 70875 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 4.5894. Min Range: -4.5894

Max Act: 4.0006. Min Act: -0.0000

Data Index: 433478 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.9164. Min Act: -0.0000

Data Index: 674792 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.8285. Min Act: -0.0000

Data Index: 1069740 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.6131. Min Act: -0.0000

Data Index: 88946 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.4183. Min Act: -0.0000

Data Index: 790840 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.7137. Min Act: -0.0000

Data Index: 393035 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.4149. Min Act: -0.0000

Data Index: 84536 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 4.5894. Min Range: -4.5894

Max Act: 3.2524. Min Act: -0.0000

Data Index: 1080063 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.8194. Min Act: -0.0000

Data Index: 1247295 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.7632. Min Act: 0.0000

Data Index: 661019 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.7877. Min Act: -0.0000

Data Index: 1020836 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.8264. Min Act: -0.0000

Data Index: 632933 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.8844. Min Act: -0.0000

Data Index: 111025 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.7269. Min Act: -0.0000

Data Index: 107124 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.7473. Min Act: -0.0000

Data Index: 847059 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 4.5894. Min Range: -4.5894

Max Act: 2.4903. Min Act: -0.0000

Data Index: 214928 (C4 (Web Text))

Max Activating Token Index: 975