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

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

Neuron 2912 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1685. Min Act: -0.0000

Data Index: 429024 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1550. Min Act: -0.0000

Data Index: 339073 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1346. Min Act: -0.0000

Data Index: 119176 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1487. Min Act: -0.0000

Data Index: 227191 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1324. Min Act: -0.0000

Data Index: 47702 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1292. Min Act: -0.0000

Data Index: 836083 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1175. Min Act: -0.0000

Data Index: 610176 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1238. Min Act: -0.0000

Data Index: 167965 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1206. Min Act: -0.0000

Data Index: 354115 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1170. Min Act: -0.0000

Data Index: 858702 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1194236 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1351657 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1067. Min Act: -0.0000

Data Index: 174920 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1175. Min Act: -0.0000

Data Index: 522280 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1110. Min Act: -0.0000

Data Index: 934053 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1288476 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1065. Min Act: -0.0000

Data Index: 858814 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1057. Min Act: -0.0000

Data Index: 828696 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1120294 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.1685. Min Range: -0.1685

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1038811 (C4 (Web Text))

Max Activating Token Index: 928