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

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

Neuron 3354 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0003

Data Index: 306723 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1615990 (Python Code)

Max Activating Token Index: 688

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0425. Min Act: -0.0003

Data Index: 649947 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0419. Min Act: -0.0003

Data Index: 624063 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0391. Min Act: -0.0003

Data Index: 144682 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1388816 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1628275 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1294353 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0400. Min Act: -0.0003

Data Index: 822402 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1022640 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0383. Min Act: -0.0003

Data Index: 816346 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1089335 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1512806 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1472828 (Python Code)

Max Activating Token Index: 545

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0367. Min Act: -0.0003

Data Index: 132457 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0373. Min Act: -0.0003

Data Index: 985410 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1264547 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1446898 (Python Code)

Max Activating Token Index: 314

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0367. Min Act: -0.0003

Data Index: 519987 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1158445 (C4 (Web Text))

Max Activating Token Index: 395