Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 264 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0374. Min Act: -0.0003

Data Index: 144749 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0307. Min Act: -0.0003

Data Index: 86299 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0347. Min Act: -0.0003

Data Index: 564686 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1004223 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0347. Min Act: -0.0003

Data Index: 453315 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1122895 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0281. Min Act: -0.0003

Data Index: 779573 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0305. Min Act: -0.0003

Data Index: 159525 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0311. Min Act: -0.0003

Data Index: 668169 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0327. Min Act: -0.0003

Data Index: 790491 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1317969 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0295. Min Act: -0.0003

Data Index: 717596 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1274049 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1299057 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0310. Min Act: -0.0003

Data Index: 88163 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0290. Min Act: -0.0003

Data Index: 997707 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1181913 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1304946 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0323. Min Act: -0.0003

Data Index: 827149 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0298. Min Act: -0.0003

Data Index: 832574 (C4 (Web Text))

Max Activating Token Index: 120