Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 338 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0003

Data Index: 673844 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0582. Min Act: -0.0003

Data Index: 843638 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1193077 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0553. Min Act: -0.0003

Data Index: 216304 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0536. Min Act: -0.0003

Data Index: 668214 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0516. Min Act: -0.0003

Data Index: 812000 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0516. Min Act: -0.0003

Data Index: 626092 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1021700 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0494. Min Act: -0.0003

Data Index: 244950 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1229653 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0484. Min Act: -0.0003

Data Index: 895952 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1223417 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0476. Min Act: -0.0003

Data Index: 255758 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0479. Min Act: -0.0003

Data Index: 231344 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0477. Min Act: -0.0003

Data Index: 813742 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0482. Min Act: -0.0003

Data Index: 294377 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0471. Min Act: -0.0003

Data Index: 858350 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1252462 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0469. Min Act: -0.0003

Data Index: 604471 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0457. Min Act: -0.0004

Data Index: 83231 (C4 (Web Text))

Max Activating Token Index: 58