Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1628 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7424. Min Act: -0.0000

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1121189 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5937. Min Act: -0.0000

Data Index: 810267 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5480. Min Act: -0.0000

Data Index: 297930 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1096876 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1144155 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4940. Min Act: -0.0000

Data Index: 842429 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1347052 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4892. Min Act: -0.0000

Data Index: 213980 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4869. Min Act: -0.0000

Data Index: 991104 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4689. Min Act: -0.0000

Data Index: 27826 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4659. Min Act: -0.0000

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4455. Min Act: -0.0000

Data Index: 485460 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4309. Min Act: -0.0000

Data Index: 858697 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5128. Min Act: -0.0000

Data Index: 140023 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4595. Min Act: -0.0000

Data Index: 307766 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4859. Min Act: -0.0000

Data Index: 837718 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4539. Min Act: -0.0000

Data Index: 67002 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1287239 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.4522. Min Act: -0.0000

Data Index: 971676 (C4 (Web Text))

Max Activating Token Index: 650