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

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

Neuron 5966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.7149. Min Act: -0.0000

Data Index: 594084 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.7146. Min Act: -0.0000

Data Index: 137535 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.8215. Min Act: -0.0000

Data Index: 89231 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.4307. Min Act: -0.0000

Data Index: 405346 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.1371. Min Act: -0.0000

Data Index: 213642 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.2163. Min Act: -0.0000

Data Index: 619664 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.2919. Min Act: -0.0000

Data Index: 1210774 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.0391. Min Act: -0.0000

Data Index: 872131 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.4576. Min Act: -0.0000

Data Index: 641986 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.8945. Min Act: -0.0000

Data Index: 1012457 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 4.8215. Min Range: -4.8215

Max Act: 4.0649. Min Act: -0.0000

Data Index: 1151766 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.7407. Min Act: -0.0000

Data Index: 757530 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.6717. Min Act: -0.0000

Data Index: 337641 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.6224. Min Act: -0.0000

Data Index: 1346314 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.6145. Min Act: -0.0000

Data Index: 751630 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.7580. Min Act: -0.0000

Data Index: 485799 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.3996. Min Act: -0.0000

Data Index: 527389 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.3585. Min Act: -0.0000

Data Index: 342757 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.6430. Min Act: -0.0000

Data Index: 507857 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 4.8215. Min Range: -4.8215

Max Act: 3.4689. Min Act: -0.0000

Data Index: 1149469 (C4 (Web Text))

Max Activating Token Index: 650