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

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

Neuron 2241 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9206. Min Act: -0.0000

Data Index: 224248 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.0166. Min Range: -1.0166

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1040116 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8675. Min Act: -0.0000

Data Index: 23236 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1312491 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.9165. Min Act: -0.0000

Data Index: 89539 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8476. Min Act: -0.0000

Data Index: 76282 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7622. Min Act: -0.0000

Data Index: 878740 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1146743 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8795. Min Act: -0.0000

Data Index: 387863 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1101542 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7782. Min Act: -0.0000

Data Index: 705094 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7738. Min Act: -0.0000

Data Index: 394116 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7077. Min Act: -0.0000

Data Index: 332587 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1168972 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.8122. Min Act: -0.0000

Data Index: 323349 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1125888 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1228827 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7157. Min Act: -0.0000

Data Index: 369052 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7077. Min Act: -0.0000

Data Index: 749573 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.0166. Min Range: -1.0166

Max Act: 0.7255. Min Act: -0.0000

Data Index: 240118 (C4 (Web Text))

Max Activating Token Index: 976