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

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

Neuron 1022 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0004

Data Index: 790613 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1338159 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0003

Data Index: 465372 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1310998 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1280014 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1034596 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0003

Data Index: 880171 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0003

Data Index: 861335 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0004

Data Index: 1074892 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0004

Data Index: 667183 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0003

Data Index: 593592 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0004

Data Index: 1321859 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0003

Data Index: 781857 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0003

Data Index: 533103 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0003

Data Index: 447892 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0003

Data Index: 322542 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0004

Data Index: 147271 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0003

Data Index: 758448 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0004

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0004

Data Index: 358729 (C4 (Web Text))

Max Activating Token Index: 395