Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4006 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0301. Min Range: -1.0301

Max Act: 1.0301. Min Act: -0.0001

Data Index: 399619 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.9129. Min Act: -0.0000

Data Index: 428436 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8988. Min Act: -0.0001

Data Index: 589842 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8244. Min Act: -0.0000

Data Index: 590294 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8261. Min Act: -0.0001

Data Index: 522730 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8073. Min Act: -0.0000

Data Index: 666125 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7823. Min Act: -0.0001

Data Index: 630805 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8171. Min Act: -0.0001

Data Index: 1325139 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7502. Min Act: -0.0000

Data Index: 310043 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7512. Min Act: -0.0001

Data Index: 622506 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7964. Min Act: -0.0001

Data Index: 904829 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7467. Min Act: -0.0001

Data Index: 772948 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7376. Min Act: -0.0001

Data Index: 1333988 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1090021 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1137705 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7275. Min Act: -0.0001

Data Index: 1110553 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7348. Min Act: -0.0000

Data Index: 478304 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1002429 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7087. Min Act: -0.0000

Data Index: 174204 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1168599 (C4 (Web Text))

Max Activating Token Index: 713