Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1813 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1102529 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.5095. Min Act: -0.0000

Data Index: 531684 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1164371 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4753. Min Act: -0.0000

Data Index: 377406 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4656. Min Act: -0.0000

Data Index: 40112 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4669. Min Act: -0.0000

Data Index: 631991 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4405. Min Act: -0.0000

Data Index: 203022 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4234. Min Act: -0.0000

Data Index: 133465 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1186175 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.4367. Min Act: -0.0000

Data Index: 178311 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3949. Min Act: -0.0000

Data Index: 719678 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1329232 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3894. Min Act: -0.0000

Data Index: 493327 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3891. Min Act: -0.0000

Data Index: 458365 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1098861 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1021134 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3810. Min Act: -0.0000

Data Index: 36137 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3800. Min Act: -0.0000

Data Index: 436565 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3895. Min Act: -0.0000

Data Index: 744410 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.5439. Min Range: -0.5439

Max Act: 0.3725. Min Act: -0.0000

Data Index: 87558 (C4 (Web Text))

Max Activating Token Index: 954