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

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

Neuron 948 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5874. Min Act: -0.0000

Data Index: 473921 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1317786 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5248. Min Act: -0.0000

Data Index: 27453 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5562. Min Act: -0.0000

Data Index: 83230 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1136276 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1204180 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4881. Min Act: -0.0000

Data Index: 955099 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4926. Min Act: -0.0000

Data Index: 100761 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1270036 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4706. Min Act: -0.0000

Data Index: 678142 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4529. Min Act: -0.0000

Data Index: 437866 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4449. Min Act: -0.0000

Data Index: 849283 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4230. Min Act: -0.0000

Data Index: 18650 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4380. Min Act: -0.0000

Data Index: 750410 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4176. Min Act: -0.0000

Data Index: 426901 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4148. Min Act: -0.0000

Data Index: 199553 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4455. Min Act: -0.0000

Data Index: 678899 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4260. Min Act: -0.0000

Data Index: 946980 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4226. Min Act: -0.0000

Data Index: 274354 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.5874. Min Range: -0.5874

Max Act: 0.4144. Min Act: -0.0000

Data Index: 670700 (C4 (Web Text))

Max Activating Token Index: 903