Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3105 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1313737 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1039661 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0131. Min Act: -0.0002

Data Index: 684452 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0130. Min Act: -0.0002

Data Index: 53082 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1263862 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0002

Data Index: 466475 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0130. Min Act: -0.0002

Data Index: 480287 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0129. Min Act: -0.0002

Data Index: 575662 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0129. Min Act: -0.0002

Data Index: 194640 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0129. Min Act: -0.0002

Data Index: 736907 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0128. Min Act: -0.0002

Data Index: 958649 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1190050 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0002

Data Index: 268257 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1164517 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0126. Min Act: -0.0002

Data Index: 309006 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0126. Min Act: -0.0002

Data Index: 350022 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1084285 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0002

Data Index: 313788 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0002

Data Index: 695856 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1054598 (C4 (Web Text))

Max Activating Token Index: 878