Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 27 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0006

Data Index: 786675 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0006

Data Index: 857465 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0152. Min Act: -0.0006

Data Index: 754523 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1140949 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0006

Data Index: 593050 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0146. Min Act: -0.0006

Data Index: 103163 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0136. Min Act: -0.0006

Data Index: 94458 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0006

Data Index: 699957 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1090047 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0140. Min Act: -0.0006

Data Index: 113868 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0143. Min Act: -0.0006

Data Index: 418081 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0136. Min Act: -0.0006

Data Index: 225294 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0006

Data Index: 53226 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0006

Data Index: 707186 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0142. Min Act: -0.0006

Data Index: 472363 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1323403 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0006

Data Index: 553431 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0137. Min Act: -0.0006

Data Index: 534229 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0137. Min Act: -0.0006

Data Index: 134388 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1009275 (C4 (Web Text))

Max Activating Token Index: 206