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

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

Neuron 1950 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.4126. Min Act: -0.0000

Data Index: 714961 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.2093. Min Act: 0.0002

Data Index: 1181491 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.1231. Min Act: -0.0000

Data Index: 470008 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 3.4126. Min Range: -3.4126

Max Act: 3.0003. Min Act: 0.0004

Data Index: 10236 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.7811. Min Act: -0.0000

Data Index: 731832 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.9273. Min Act: -0.0000

Data Index: 1144596 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.8538. Min Act: 0.0000

Data Index: 1273232 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.5403. Min Act: 0.0003

Data Index: 40399 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.6381. Min Act: 0.0000

Data Index: 111035 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.6177. Min Act: -0.0000

Data Index: 109426 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.4975. Min Act: 0.0001

Data Index: 1122037 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.5674. Min Act: -0.0000

Data Index: 1255267 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.5562. Min Act: -0.0000

Data Index: 626843 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.6431. Min Act: -0.0000

Data Index: 1081963 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.5108. Min Act: -0.0000

Data Index: 19250 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.6403. Min Act: -0.0000

Data Index: 751541 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.4919. Min Act: -0.0000

Data Index: 315773 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.4891. Min Act: 0.0001

Data Index: 104425 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.4963. Min Act: -0.0000

Data Index: 1255269 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.4126. Min Range: -3.4126

Max Act: 2.4870. Min Act: 0.0004

Data Index: 750383 (C4 (Web Text))

Max Activating Token Index: 555