Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3954 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1482485 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1636252 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1578264 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1636395 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1365608 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1394100 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1371415 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1413680 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1494520 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1508133 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1512695 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1446576 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1480930 (Python Code)

Max Activating Token Index: 282

Text #13

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1491304 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1543456 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1646233 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1380677 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1561403 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1418179 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1623525 (Python Code)

Max Activating Token Index: 29