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

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

Neuron 53 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1116. Min Act: -0.0001

Data Index: 455372 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1126. Min Act: -0.0001

Data Index: 61371 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1113. Min Act: -0.0001

Data Index: 283583 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1089. Min Act: -0.0001

Data Index: 829715 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1083. Min Act: -0.0001

Data Index: 15288 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1123. Min Act: -0.0001

Data Index: 14813 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1135. Min Act: -0.0001

Data Index: 325354 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1090. Min Act: -0.0001

Data Index: 182791 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1054. Min Act: -0.0001

Data Index: 740048 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1127. Min Act: -0.0001

Data Index: 537207 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1275955 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1041. Min Act: -0.0001

Data Index: 491796 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1069. Min Act: -0.0001

Data Index: 885299 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1073. Min Act: -0.0001

Data Index: 737029 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1051. Min Act: -0.0001

Data Index: 323283 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1130. Min Act: -0.0001

Data Index: 784721 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1062624 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1126. Min Act: -0.0001

Data Index: 458366 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.0974. Min Act: -0.0001

Data Index: 236162 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.1135. Min Range: -0.1135

Max Act: 0.1029. Min Act: -0.0001

Data Index: 965389 (C4 (Web Text))

Max Activating Token Index: 311