Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 522 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0132. Min Act: -0.0006

Data Index: 404426 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0006

Data Index: 773763 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0131. Min Act: -0.0006

Data Index: 549332 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0128. Min Act: -0.0006

Data Index: 863449 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0127. Min Act: -0.0006

Data Index: 384992 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0128. Min Act: -0.0006

Data Index: 450785 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1320195 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0006

Data Index: 887845 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0121. Min Act: -0.0006

Data Index: 403629 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1273517 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0006

Data Index: 318151 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0006

Data Index: 198111 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1341003 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0006

Data Index: 890247 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0118. Min Act: -0.0006

Data Index: 872104 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0121. Min Act: -0.0006

Data Index: 386030 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0006

Data Index: 585949 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0006

Data Index: 412289 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0120. Min Act: -0.0006

Data Index: 907681 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0006

Data Index: 973034 (C4 (Web Text))

Max Activating Token Index: 554