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

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

Neuron 125 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: 2.8311. Min Range: -2.8311

Max Act: 2.8311. Min Act: -0.0002

Data Index: 636041 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.7640. Min Act: -0.0002

Data Index: 1045673 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.7408. Min Act: -0.0002

Data Index: 291313 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5896. Min Act: -0.0002

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5362. Min Act: -0.0002

Data Index: 661894 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5966. Min Act: -0.0002

Data Index: 479966 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5806. Min Act: -0.0002

Data Index: 1091545 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5598. Min Act: -0.0002

Data Index: 726075 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5486. Min Act: -0.0002

Data Index: 58855 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5712. Min Act: -0.0002

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.6135. Min Act: -0.0002

Data Index: 927017 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5988. Min Act: -0.0002

Data Index: 1097004 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.6072. Min Act: -0.0002

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5188. Min Act: -0.0002

Data Index: 813743 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5960. Min Act: -0.0002

Data Index: 326412 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5960. Min Act: -0.0002

Data Index: 529244 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5960. Min Act: -0.0002

Data Index: 526224 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5960. Min Act: -0.0002

Data Index: 316652 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5960. Min Act: -0.0002

Data Index: 284490 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 2.8311. Min Range: -2.8311

Max Act: 2.5960. Min Act: -0.0002

Data Index: 42221 (C4 (Web Text))

Max Activating Token Index: 2