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

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

Neuron 619 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1555. Min Act: -0.0001

Data Index: 548503 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1614161 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1373882 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1348781 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1300. Min Act: -0.0000

Data Index: 974058 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1152. Min Act: -0.0001

Data Index: 281550 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1420717 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1188. Min Act: -0.0000

Data Index: 368708 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1207. Min Act: -0.0001

Data Index: 238160 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1154. Min Act: -0.0001

Data Index: 519783 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1635697 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1175. Min Act: -0.0001

Data Index: 465956 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1163. Min Act: -0.0000

Data Index: 88217 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1188. Min Act: -0.0001

Data Index: 459743 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1109. Min Act: -0.0001

Data Index: 606522 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1142. Min Act: -0.0000

Data Index: 483600 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1140. Min Act: -0.0001

Data Index: 896165 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1101. Min Act: -0.0000

Data Index: 947281 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1123. Min Act: -0.0001

Data Index: 238572 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1162. Min Act: -0.0000

Data Index: 964080 (C4 (Web Text))

Max Activating Token Index: 579