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

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

Neuron 967 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.8887. Min Act: -0.0000

Data Index: 69358 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.6999. Min Act: -0.0000

Data Index: 22893 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.5495. Min Act: -0.0000

Data Index: 991920 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.6215. Min Act: -0.0000

Data Index: 628807 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.5858. Min Act: -0.0000

Data Index: 844301 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.5216. Min Act: -0.0000

Data Index: 211814 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.4159. Min Act: -0.0000

Data Index: 139676 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.3870. Min Act: -0.0000

Data Index: 508595 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.3869. Min Act: -0.0000

Data Index: 795369 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.3636. Min Act: -0.0000

Data Index: 1344210 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.3534. Min Act: -0.0000

Data Index: 1186171 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.2940. Min Act: -0.0000

Data Index: 1099913 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.3730. Min Act: -0.0000

Data Index: 414624 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.3429. Min Act: -0.0000

Data Index: 1022406 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.2246. Min Act: -0.0000

Data Index: 1268587 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.1177. Min Act: -0.0000

Data Index: 925314 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.1178. Min Act: -0.0000

Data Index: 1298127 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.1107. Min Act: -0.0000

Data Index: 1254065 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 2.8887. Min Range: -2.8887

Max Act: 2.0665. Min Act: -0.0000

Data Index: 1014528 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 2.8887. Min Range: -2.8887

Max Act: 1.9338. Min Act: -0.0000

Data Index: 690954 (C4 (Web Text))

Max Activating Token Index: 910