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

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

Neuron 4555 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2269. Min Range: -3.2269

Max Act: 3.2269. Min Act: -0.0000

Data Index: 916507 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.7991. Min Act: -0.0000

Data Index: 691340 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.7310. Min Act: -0.0000

Data Index: 1294340 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.7297. Min Act: -0.0000

Data Index: 61449 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.6287. Min Act: -0.0000

Data Index: 976366 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.5993. Min Act: -0.0000

Data Index: 810329 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.5894. Min Act: -0.0000

Data Index: 1286612 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.3614. Min Act: -0.0000

Data Index: 1318736 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.4269. Min Act: -0.0000

Data Index: 487589 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.5186. Min Act: -0.0000

Data Index: 404530 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.3548. Min Act: -0.0000

Data Index: 838070 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.4824. Min Act: -0.0000

Data Index: 971379 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.3543. Min Act: -0.0000

Data Index: 951282 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.3437. Min Act: -0.0000

Data Index: 950599 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.3037. Min Act: -0.0000

Data Index: 852732 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.3735. Min Act: -0.0000

Data Index: 685523 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.3703. Min Act: -0.0000

Data Index: 790315 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.2469. Min Act: -0.0000

Data Index: 274732 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.2220. Min Act: -0.0000

Data Index: 1320025 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 3.2269. Min Range: -3.2269

Max Act: 2.2251. Min Act: -0.0000

Data Index: 609119 (C4 (Web Text))

Max Activating Token Index: 579