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

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

Neuron 4451 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1583287 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1056867 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1453509 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1466901 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1425130 (Python Code)

Max Activating Token Index: 195

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1438480 (Python Code)

Max Activating Token Index: 815

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1586163 (Python Code)

Max Activating Token Index: 928

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0228. Min Act: -0.0001

Data Index: 1531740 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0230. Min Act: -0.0001

Data Index: 974669 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1563140 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1512044 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1591245 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1531123 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1576457 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1436005 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1402640 (Python Code)

Max Activating Token Index: 150

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0214. Min Act: -0.0001

Data Index: 700882 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1559597 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1585068 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1588133 (Python Code)

Max Activating Token Index: 609