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

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

Neuron 5160 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: 0.5218. Min Range: -0.5218

Max Act: 0.5218. Min Act: -0.0001

Data Index: 266236 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.5022. Min Act: -0.0001

Data Index: 806468 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4877. Min Act: -0.0001

Data Index: 160234 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4739. Min Act: -0.0001

Data Index: 273927 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4389. Min Act: -0.0001

Data Index: 367592 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4297. Min Act: -0.0001

Data Index: 503327 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4333. Min Act: -0.0001

Data Index: 944800 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4244. Min Act: -0.0001

Data Index: 429657 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4284. Min Act: -0.0001

Data Index: 264536 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4144. Min Act: -0.0001

Data Index: 778130 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4177. Min Act: -0.0001

Data Index: 1338382 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4045. Min Act: -0.0001

Data Index: 368942 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3996. Min Act: -0.0001

Data Index: 955407 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4015. Min Act: -0.0001

Data Index: 1211543 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4065. Min Act: -0.0001

Data Index: 711629 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3953. Min Act: -0.0001

Data Index: 1104033 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3936. Min Act: -0.0001

Data Index: 1050741 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3872. Min Act: -0.0001

Data Index: 1084276 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3863. Min Act: -0.0001

Data Index: 1063781 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3739. Min Act: -0.0001

Data Index: 1247776 (C4 (Web Text))

Max Activating Token Index: 455