Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 149 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0141. Min Act: -0.0006

Data Index: 946770 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0006

Data Index: 873863 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0138. Min Act: -0.0006

Data Index: 57730 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1340745 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0132. Min Act: -0.0006

Data Index: 45996 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0139. Min Act: -0.0006

Data Index: 805732 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1123348 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0135. Min Act: -0.0006

Data Index: 729715 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1036358 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1052071 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0137. Min Act: -0.0006

Data Index: 367582 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1080368 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1133409 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0006

Data Index: 632628 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0006

Data Index: 269549 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0006

Data Index: 679657 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0006

Data Index: 589268 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1257441 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1007497 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1304593 (C4 (Web Text))

Max Activating Token Index: 1005