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

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

Neuron 3416 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1164133 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0162. Min Act: -0.0002

Data Index: 177637 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0155. Min Act: -0.0002

Data Index: 287062 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0002

Data Index: 61253 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0144. Min Act: -0.0002

Data Index: 108076 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0143. Min Act: -0.0002

Data Index: 827503 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0002

Data Index: 902369 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0142. Min Act: -0.0002

Data Index: 439560 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1115201 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0002

Data Index: 500480 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0002

Data Index: 95985 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0140. Min Act: -0.0002

Data Index: 198601 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0002

Data Index: 109839 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0137. Min Act: -0.0002

Data Index: 89270 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1327775 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1214707 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1609783 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0135. Min Act: -0.0002

Data Index: 767200 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1231702 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0134. Min Act: -0.0003

Data Index: 671880 (C4 (Web Text))

Max Activating Token Index: 536