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

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

Neuron 1272 in Layer 0

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: 0.6215. Min Range: -0.6215

Max Act: 0.6215. Min Act: -0.0001

Data Index: 800134 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6169. Min Act: -0.0001

Data Index: 557893 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6203. Min Act: -0.0001

Data Index: 1232882 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6064. Min Act: -0.0001

Data Index: 938631 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5448. Min Act: -0.0001

Data Index: 1152011 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5402. Min Act: -0.0001

Data Index: 999573 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5323. Min Act: -0.0001

Data Index: 737526 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5389. Min Act: -0.0001

Data Index: 211358 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5347. Min Act: -0.0001

Data Index: 765576 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5292. Min Act: -0.0001

Data Index: 635207 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5270. Min Act: -0.0001

Data Index: 1125290 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5196. Min Act: -0.0001

Data Index: 592460 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5148. Min Act: -0.0001

Data Index: 1321992 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5272. Min Act: -0.0001

Data Index: 163284 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5100. Min Act: -0.0001

Data Index: 930526 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5073. Min Act: -0.0001

Data Index: 715187 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5058. Min Act: -0.0001

Data Index: 258049 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5050. Min Act: -0.0001

Data Index: 84181 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5046. Min Act: -0.0001

Data Index: 1074791 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4896. Min Act: -0.0001

Data Index: 1262315 (C4 (Web Text))

Max Activating Token Index: 313