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

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

Neuron 1508 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: 2.2229. Min Range: -2.2229

Max Act: 2.2229. Min Act: -0.0002

Data Index: 204035 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.2229. Min Range: -2.2229

Max Act: 2.0135. Min Act: -0.0002

Data Index: 1045613 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.9352. Min Act: -0.0002

Data Index: 656974 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.9005. Min Act: -0.0002

Data Index: 778551 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.8801. Min Act: -0.0002

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.8498. Min Act: -0.0002

Data Index: 902319 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.7026. Min Act: -0.0002

Data Index: 493575 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.5344. Min Act: -0.0002

Data Index: 1349461 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4887. Min Act: -0.0002

Data Index: 187988 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.5442. Min Act: -0.0002

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.5739. Min Act: -0.0002

Data Index: 502094 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4622. Min Act: -0.0002

Data Index: 68048 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4628. Min Act: -0.0002

Data Index: 16049 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4397. Min Act: -0.0002

Data Index: 1150805 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4789. Min Act: -0.0002

Data Index: 932849 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4134. Min Act: -0.0002

Data Index: 103462 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4180. Min Act: -0.0002

Data Index: 1227615 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4146. Min Act: -0.0002

Data Index: 818731 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.3993. Min Act: -0.0002

Data Index: 147949 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.2229. Min Range: -2.2229

Max Act: 1.4268. Min Act: -0.0002

Data Index: 178228 (C4 (Web Text))

Max Activating Token Index: 883