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

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

Neuron 4975 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.5805. Min Act: -0.0001

Data Index: 111229 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.5949. Min Act: -0.0001

Data Index: 1154440 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.5374. Min Act: -0.0001

Data Index: 1199047 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.1649. Min Act: -0.0001

Data Index: 1073176 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.4301. Min Act: -0.0001

Data Index: 1172253 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.3568. Min Act: -0.0001

Data Index: 1057792 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.3514. Min Act: -0.0001

Data Index: 1136492 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.4552. Min Act: -0.0001

Data Index: 511722 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2709. Min Act: -0.0001

Data Index: 1338392 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2516. Min Act: -0.0001

Data Index: 720000 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2005. Min Act: -0.0000

Data Index: 390321 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2927. Min Act: -0.0001

Data Index: 1355595 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.1681. Min Act: -0.0001

Data Index: 1289406 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1248837 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2433. Min Act: -0.0001

Data Index: 670588 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2181. Min Act: -0.0001

Data Index: 12803 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2451. Min Act: -0.0001

Data Index: 771216 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.2506. Min Act: -0.0001

Data Index: 567796 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1235663 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.5949. Min Range: -1.5949

Max Act: 1.1489. Min Act: -0.0001

Data Index: 647359 (C4 (Web Text))

Max Activating Token Index: 536