Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3815 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1119. Min Range: -2.1119

Max Act: 2.1119. Min Act: -0.0001

Data Index: 221386 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.2766. Min Act: -0.0001

Data Index: 1023611 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0583. Min Act: -0.0001

Data Index: 365429 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.5385. Min Act: -0.0001

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.1801. Min Act: -0.0001

Data Index: 270340 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0546. Min Act: -0.0001

Data Index: 1272835 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.1540. Min Act: -0.0000

Data Index: 904734 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.1004. Min Act: -0.0001

Data Index: 380758 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 2.1119. Min Range: -2.1119

Max Act: 0.9969. Min Act: -0.0001

Data Index: 563087 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.1142. Min Act: -0.0000

Data Index: 366329 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.2134. Min Act: -0.0001

Data Index: 843364 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0448. Min Act: -0.0000

Data Index: 738171 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.1118. Min Act: -0.0000

Data Index: 45683 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0424. Min Act: -0.0001

Data Index: 1167237 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1133801 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0672. Min Act: -0.0001

Data Index: 872053 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0870. Min Act: -0.0000

Data Index: 559237 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.1377. Min Act: -0.0000

Data Index: 719654 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0280. Min Act: -0.0000

Data Index: 360890 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 2.1119. Min Range: -2.1119

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1322414 (C4 (Web Text))

Max Activating Token Index: 179