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

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

Neuron 3031 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1310832 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1155724 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0477. Min Act: -0.0001

Data Index: 1249528 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0326. Min Act: -0.0001

Data Index: 700152 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0351. Min Act: -0.0001

Data Index: 616915 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0320. Min Act: -0.0001

Data Index: 106740 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0343. Min Act: -0.0001

Data Index: 552943 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1011219 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0322. Min Act: -0.0001

Data Index: 3382 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1215742 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1245065 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1308508 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0311. Min Act: -0.0001

Data Index: 770411 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0310. Min Act: -0.0001

Data Index: 560643 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0290. Min Act: -0.0001

Data Index: 191416 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1459403 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1197513 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1030813 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0268. Min Act: -0.0001

Data Index: 475135 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0288. Min Act: -0.0001

Data Index: 244887 (C4 (Web Text))

Max Activating Token Index: 329