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

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

Neuron 5804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.9493. Min Act: -0.0000

Data Index: 22751 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7277. Min Act: -0.0000

Data Index: 986089 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6992. Min Act: -0.0000

Data Index: 120352 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6825. Min Act: -0.0000

Data Index: 784561 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6941. Min Act: -0.0000

Data Index: 818344 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1335072 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1139925 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6583. Min Act: -0.0000

Data Index: 10670 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6981. Min Act: -0.0000

Data Index: 438542 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1041336 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6009. Min Act: -0.0000

Data Index: 69723 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.5996. Min Act: -0.0000

Data Index: 469385 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6358. Min Act: -0.0000

Data Index: 586533 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.5944. Min Act: -0.0000

Data Index: 763310 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.5915. Min Act: -0.0000

Data Index: 493684 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1038494 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1115058 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.5888. Min Act: -0.0000

Data Index: 797722 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.5862. Min Act: -0.0000

Data Index: 76360 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6027. Min Act: -0.0000

Data Index: 496891 (C4 (Web Text))

Max Activating Token Index: 34