Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 493 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.2247. Min Act: -0.0002

Data Index: 1402465 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1955. Min Act: -0.0002

Data Index: 1438881 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1485. Min Act: -0.0002

Data Index: 1395112 (Python Code)

Max Activating Token Index: 724

Text #3

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1534471 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1582317 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1340. Min Act: -0.0002

Data Index: 832474 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1611346 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1375258 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1438534 (Python Code)

Max Activating Token Index: 365

Text #9

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1613921 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1437147 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1147. Min Act: -0.0002

Data Index: 1547763 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1465995 (Python Code)

Max Activating Token Index: 880

Text #13

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1127. Min Act: -0.0002

Data Index: 295786 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1553620 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1427249 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1375083 (Python Code)

Max Activating Token Index: 256

Text #17

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1558063 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1480671 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1439270 (Python Code)

Max Activating Token Index: 58