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

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

Neuron 5075 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: 0.6769. Min Range: -0.6769

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1324999 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5875. Min Act: -0.0000

Data Index: 947085 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.5663. Min Act: -0.0000

Data Index: 695273 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4904. Min Act: -0.0000

Data Index: 575019 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4998. Min Act: -0.0000

Data Index: 30996 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4512. Min Act: -0.0000

Data Index: 759114 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4058. Min Act: -0.0000

Data Index: 238505 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4224. Min Act: -0.0000

Data Index: 13815 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4008. Min Act: -0.0000

Data Index: 651382 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1225726 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3919. Min Act: -0.0000

Data Index: 354764 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1009049 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3835. Min Act: -0.0000

Data Index: 480395 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3665. Min Act: -0.0000

Data Index: 204755 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3587. Min Act: -0.0000

Data Index: 173162 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3693. Min Act: -0.0000

Data Index: 1039230 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3523. Min Act: -0.0000

Data Index: 372042 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1125023 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3333. Min Act: -0.0000

Data Index: 551595 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.6769. Min Range: -0.6769

Max Act: 0.3459. Min Act: -0.0000

Data Index: 839323 (C4 (Web Text))

Max Activating Token Index: 904