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

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

Neuron 3368 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.5609. Min Act: -0.0000

Data Index: 143541 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1223438 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1124950 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1349145 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4139. Min Act: -0.0000

Data Index: 179347 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3915. Min Act: -0.0000

Data Index: 483536 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3349. Min Act: -0.0000

Data Index: 53845 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3169. Min Act: -0.0000

Data Index: 676928 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1252366 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3074. Min Act: -0.0000

Data Index: 67858 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3089. Min Act: -0.0000

Data Index: 986473 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2953. Min Act: -0.0000

Data Index: 318888 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2916. Min Act: -0.0000

Data Index: 275563 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1324535 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2935. Min Act: -0.0000

Data Index: 550985 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3014. Min Act: -0.0000

Data Index: 283107 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2899. Min Act: -0.0000

Data Index: 379849 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1095646 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2713. Min Act: -0.0000

Data Index: 630308 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.2605. Min Act: -0.0000

Data Index: 280044 (C4 (Web Text))

Max Activating Token Index: 676