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

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

Neuron 1706 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: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0006

Data Index: 571536 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0152. Min Act: -0.0006

Data Index: 472639 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0152. Min Act: -0.0006

Data Index: 670499 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0148. Min Act: -0.0006

Data Index: 141598 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0147. Min Act: -0.0006

Data Index: 666078 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0147. Min Act: -0.0006

Data Index: 694049 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0147. Min Act: -0.0006

Data Index: 927878 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0006

Data Index: 538496 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1246145 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0143. Min Act: -0.0006

Data Index: 641061 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0006

Data Index: 117960 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0006

Data Index: 85031 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0135. Min Act: -0.0006

Data Index: 730465 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1092216 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1161563 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0137. Min Act: -0.0006

Data Index: 366440 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0134. Min Act: -0.0006

Data Index: 662282 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0140. Min Act: -0.0006

Data Index: 491250 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1041580 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0006

Data Index: 77196 (C4 (Web Text))

Max Activating Token Index: 420