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

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

Neuron 213 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: 0.0181. Min Range: -0.0181

Max Act: 0.0181. Min Act: -0.0006

Data Index: 56932 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0172. Min Act: -0.0006

Data Index: 98614 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0166. Min Act: -0.0006

Data Index: 380163 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0160. Min Act: -0.0006

Data Index: 838797 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1165871 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0160. Min Act: -0.0006

Data Index: 630487 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0159. Min Act: -0.0006

Data Index: 482467 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0158. Min Act: -0.0006

Data Index: 336173 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1199071 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0155. Min Act: -0.0006

Data Index: 183872 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0155. Min Act: -0.0006

Data Index: 514256 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0154. Min Act: -0.0006

Data Index: 545247 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0154. Min Act: -0.0006

Data Index: 105280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0150. Min Act: -0.0006

Data Index: 662873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0153. Min Act: -0.0006

Data Index: 4359 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0152. Min Act: -0.0006

Data Index: 615620 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0150. Min Act: -0.0006

Data Index: 14302 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1096097 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0146. Min Act: -0.0006

Data Index: 861580 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1264336 (C4 (Web Text))

Max Activating Token Index: 461