Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1673981 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1261504 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1719964 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1155049 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1454. Min Act: -0.0000

Data Index: 943638 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1067828 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1404. Min Act: -0.0000

Data Index: 674878 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1066. Min Act: -0.0000

Data Index: 201539 (The Pile)

Max Activating Token Index: 822

Text #8

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1251. Min Act: -0.0000

Data Index: 817632 (The Pile)

Max Activating Token Index: 668

Text #9

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1183960 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1277. Min Act: 0.0000

Data Index: 275568 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1187198 (The Pile)

Max Activating Token Index: 998

Text #12

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1476559 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1144. Min Act: -0.0000

Data Index: 253066 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1147. Min Act: -0.0000

Data Index: 478216 (The Pile)

Max Activating Token Index: 793

Text #15

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1183. Min Act: 0.0000

Data Index: 1873580 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1088085 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1102198 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1557776 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1165. Min Act: 0.0000

Data Index: 1200374 (The Pile)

Max Activating Token Index: 673