Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4402 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.4026. Min Act: -0.0001

Data Index: 94100 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.4025. Min Act: -0.0001

Data Index: 480664 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.4049. Min Act: -0.0001

Data Index: 1095850 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3749. Min Act: -0.0001

Data Index: 206821 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3938. Min Act: -0.0001

Data Index: 638415 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3511. Min Act: -0.0001

Data Index: 531985 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3727. Min Act: -0.0001

Data Index: 473468 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3720. Min Act: -0.0001

Data Index: 803247 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3286. Min Act: -0.0001

Data Index: 429572 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3438. Min Act: -0.0001

Data Index: 322509 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3257. Min Act: -0.0001

Data Index: 672258 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3418. Min Act: -0.0001

Data Index: 1247671 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3548. Min Act: -0.0001

Data Index: 757265 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3364. Min Act: -0.0001

Data Index: 473438 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3928. Min Act: -0.0001

Data Index: 1320429 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3290. Min Act: -0.0001

Data Index: 656520 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3318. Min Act: -0.0001

Data Index: 537479 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3101. Min Act: -0.0001

Data Index: 1307635 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3182. Min Act: -0.0001

Data Index: 137250 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3246. Min Act: -0.0001

Data Index: 529559 (C4 (Web Text))

Max Activating Token Index: 938