Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0005

Data Index: 1011072 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0506. Min Act: -0.0005

Data Index: 1341804 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0477. Min Act: -0.0005

Data Index: 322898 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0467. Min Act: -0.0005

Data Index: 954314 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0403. Min Act: -0.0005

Data Index: 61928 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0424. Min Act: -0.0005

Data Index: 31487 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0405. Min Act: -0.0005

Data Index: 458632 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0395. Min Act: -0.0005

Data Index: 1121077 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0419. Min Act: -0.0005

Data Index: 1281151 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0429. Min Act: -0.0005

Data Index: 254015 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0411. Min Act: -0.0005

Data Index: 391304 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0437. Min Act: -0.0005

Data Index: 805496 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0410. Min Act: -0.0005

Data Index: 550883 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1126598 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0376. Min Act: -0.0005

Data Index: 517753 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0392. Min Act: -0.0005

Data Index: 962757 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0394. Min Act: -0.0005

Data Index: 99159 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0395. Min Act: -0.0005

Data Index: 354689 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0376. Min Act: -0.0005

Data Index: 471267 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0396. Min Act: -0.0005

Data Index: 256237 (C4 (Web Text))

Max Activating Token Index: 229