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

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

Neuron 484 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: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0002

Data Index: 512998 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0154. Min Act: -0.0002

Data Index: 402117 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0150. Min Act: -0.0002

Data Index: 888786 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0145. Min Act: -0.0002

Data Index: 308180 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0147. Min Act: -0.0002

Data Index: 632066 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0149. Min Act: -0.0002

Data Index: 327816 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0143. Min Act: -0.0002

Data Index: 994170 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0003

Data Index: 289402 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0141. Min Act: -0.0002

Data Index: 870949 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0002

Data Index: 856962 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0134. Min Act: -0.0002

Data Index: 325279 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1222140 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0136. Min Act: -0.0002

Data Index: 495675 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0002

Data Index: 633104 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1221275 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0133. Min Act: -0.0002

Data Index: 886149 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0135. Min Act: -0.0002

Data Index: 6667 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0139. Min Act: -0.0003

Data Index: 304977 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0137. Min Act: -0.0002

Data Index: 519399 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1356503 (C4 (Web Text))

Max Activating Token Index: 16