Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 862 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1167. Min Act: -0.0001

Data Index: 776250 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1152. Min Act: -0.0001

Data Index: 315044 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1142. Min Act: -0.0001

Data Index: 54498 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1134. Min Act: -0.0001

Data Index: 950097 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1070. Min Act: -0.0001

Data Index: 54405 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1111. Min Act: -0.0001

Data Index: 888423 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1055. Min Act: -0.0001

Data Index: 885777 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1034. Min Act: -0.0001

Data Index: 586765 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1010. Min Act: -0.0001

Data Index: 450232 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1000. Min Act: -0.0001

Data Index: 489270 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1000. Min Act: -0.0001

Data Index: 219561 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1170542 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1005638 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1005806 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1333540 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0966. Min Act: -0.0001

Data Index: 132281 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1138248 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0973. Min Act: -0.0001

Data Index: 636782 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0937. Min Act: -0.0001

Data Index: 250077 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0917. Min Act: -0.0001

Data Index: 815567 (C4 (Web Text))

Max Activating Token Index: 589