Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.2816. Min Act: -0.0001

Data Index: 1019992 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0511. Min Act: -0.0001

Data Index: 893411 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0790. Min Act: -0.0001

Data Index: 433217 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0169. Min Act: -0.0001

Data Index: 1171162 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0254. Min Act: -0.0001

Data Index: 150229 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9699. Min Act: -0.0001

Data Index: 470196 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9844. Min Act: -0.0001

Data Index: 468242 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9810. Min Act: -0.0001

Data Index: 533750 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1184236 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1194273 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0997. Min Act: -0.0001

Data Index: 43218 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9695. Min Act: -0.0001

Data Index: 594407 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9395. Min Act: -0.0001

Data Index: 1224990 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.7638. Min Act: -0.0001

Data Index: 749188 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9197. Min Act: -0.0001

Data Index: 376780 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9513. Min Act: -0.0001

Data Index: 81878 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0052. Min Act: -0.0001

Data Index: 920479 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9704. Min Act: -0.0001

Data Index: 1357854 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9009. Min Act: -0.0001

Data Index: 262483 (C4 (Web Text))

Max Activating Token Index: 19