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

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

Neuron 3208 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.9039. Min Act: -0.0000

Data Index: 201280 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.9657. Min Act: -0.0000

Data Index: 859523 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.7241. Min Act: -0.0000

Data Index: 870399 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.4746. Min Act: -0.0000

Data Index: 552170 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.5151. Min Act: -0.0000

Data Index: 1171024 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.3376. Min Act: -0.0000

Data Index: 511085 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.4466. Min Act: -0.0000

Data Index: 482704 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.3369. Min Act: -0.0000

Data Index: 518306 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.2299. Min Act: -0.0000

Data Index: 388579 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.1207. Min Act: -0.0000

Data Index: 1096768 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.0536. Min Act: -0.0000

Data Index: 617948 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 2.9657. Min Range: -2.9657

Max Act: 1.9687. Min Act: -0.0000

Data Index: 409500 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.1186. Min Act: -0.0000

Data Index: 994949 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.0978. Min Act: -0.0000

Data Index: 539358 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.2576. Min Act: -0.0000

Data Index: 53419 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 2.9657. Min Range: -2.9657

Max Act: 1.9708. Min Act: -0.0000

Data Index: 755848 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.9657. Min Range: -2.9657

Max Act: 1.9278. Min Act: -0.0000

Data Index: 102841 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 2.9657. Min Range: -2.9657

Max Act: 2.0082. Min Act: -0.0000

Data Index: 66094 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 2.9657. Min Range: -2.9657

Max Act: 1.9129. Min Act: -0.0000

Data Index: 669909 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 2.9657. Min Range: -2.9657

Max Act: 1.9656. Min Act: -0.0000

Data Index: 155954 (C4 (Web Text))

Max Activating Token Index: 643