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

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

Neuron 857 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1015584 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7945. Min Act: -0.0000

Data Index: 115235 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7106. Min Act: -0.0000

Data Index: 261724 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5990. Min Act: -0.0000

Data Index: 429161 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5251. Min Act: -0.0000

Data Index: 583495 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.6150. Min Act: -0.0000

Data Index: 201045 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1153213 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5226. Min Act: -0.0000

Data Index: 230065 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5399. Min Act: -0.0000

Data Index: 731880 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1054088 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1432343 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5168. Min Act: -0.0000

Data Index: 955248 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5071. Min Act: -0.0000

Data Index: 646056 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5090. Min Act: -0.0000

Data Index: 388745 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.5134. Min Act: -0.0000

Data Index: 538697 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.4833. Min Act: -0.0000

Data Index: 937797 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1049786 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.4773. Min Act: -0.0000

Data Index: 761439 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.4639. Min Act: -0.0000

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1016241 (C4 (Web Text))

Max Activating Token Index: 451