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

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

Neuron 999 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0001

Data Index: 375857 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0166. Min Act: -0.0001

Data Index: 633991 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0156. Min Act: -0.0001

Data Index: 738920 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1067754 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1005575 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0150. Min Act: -0.0001

Data Index: 840667 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0134. Min Act: -0.0001

Data Index: 844187 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0136. Min Act: -0.0001

Data Index: 571579 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0076. Min Act: -0.0001

Data Index: 1215511 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0136. Min Act: -0.0001

Data Index: 551626 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0083. Min Act: -0.0001

Data Index: 173648 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1213620 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0144. Min Act: -0.0001

Data Index: 521041 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1244980 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0132. Min Act: -0.0001

Data Index: 1152083 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0141. Min Act: -0.0001

Data Index: 214530 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0124. Min Act: -0.0001

Data Index: 603620 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0131. Min Act: -0.0001

Data Index: 426730 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0134. Min Act: -0.0001

Data Index: 1352507 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0094. Min Act: -0.0001

Data Index: 192007 (C4 (Web Text))

Max Activating Token Index: 594