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

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

Neuron 3403 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.3376. Min Act: -0.0000

Data Index: 670671 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1109648 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.3155. Min Act: -0.0001

Data Index: 468730 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.3053. Min Act: -0.0001

Data Index: 478121 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.3068. Min Act: -0.0000

Data Index: 335302 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2946. Min Act: -0.0000

Data Index: 294887 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2735. Min Act: -0.0001

Data Index: 1028363 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2786. Min Act: -0.0001

Data Index: 378217 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2767. Min Act: -0.0000

Data Index: 896359 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2784. Min Act: -0.0001

Data Index: 1161268 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2385. Min Act: -0.0001

Data Index: 102282 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2623. Min Act: -0.0001

Data Index: 47948 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2552. Min Act: -0.0001

Data Index: 742541 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2631. Min Act: -0.0001

Data Index: 1273650 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2574. Min Act: -0.0000

Data Index: 176013 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2560. Min Act: -0.0001

Data Index: 841407 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2365. Min Act: -0.0000

Data Index: 788529 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2548. Min Act: -0.0001

Data Index: 599360 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2369. Min Act: -0.0001

Data Index: 601300 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.3376. Min Range: -0.3376

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1086565 (C4 (Web Text))

Max Activating Token Index: 771