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

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

Neuron 3 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: 0.5684. Min Range: -0.5684

Max Act: 0.5621. Min Act: -0.0001

Data Index: 230154 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5684. Min Act: -0.0002

Data Index: 709762 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5496. Min Act: -0.0001

Data Index: 864769 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1016906 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5391. Min Act: -0.0001

Data Index: 525668 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5341. Min Act: -0.0001

Data Index: 552455 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5296. Min Act: -0.0001

Data Index: 1115879 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5217. Min Act: -0.0002

Data Index: 1202098 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5247. Min Act: -0.0001

Data Index: 120566 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5287. Min Act: -0.0001

Data Index: 15526 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5388. Min Act: -0.0001

Data Index: 1307649 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5379. Min Act: -0.0001

Data Index: 705132 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5181. Min Act: -0.0001

Data Index: 349206 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5321. Min Act: -0.0001

Data Index: 1200207 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5116. Min Act: -0.0001

Data Index: 695806 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5184. Min Act: -0.0001

Data Index: 826289 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5075. Min Act: -0.0001

Data Index: 707690 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5123. Min Act: -0.0001

Data Index: 189511 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.5213. Min Act: -0.0001

Data Index: 550156 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.5684. Min Range: -0.5684

Max Act: 0.4965. Min Act: -0.0001

Data Index: 1146542 (C4 (Web Text))

Max Activating Token Index: 289