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

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

Neuron 1020 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: 0.4219. Min Range: -0.4219

Max Act: 0.4053. Min Act: -0.0000

Data Index: 542847 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3993. Min Act: -0.0000

Data Index: 280655 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4219. Min Act: -0.0000

Data Index: 147658 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.4052. Min Act: -0.0000

Data Index: 339070 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3680. Min Act: -0.0000

Data Index: 361432 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1460433 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3549. Min Act: -0.0000

Data Index: 979681 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1599949 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1592138 (Python Code)

Max Activating Token Index: 750

Text #9

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3233. Min Act: -0.0001

Data Index: 1533643 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.3153. Min Act: -0.0001

Data Index: 1647946 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1379187 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2927. Min Act: -0.0001

Data Index: 1426461 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1568568 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2792. Min Act: -0.0000

Data Index: 518001 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2754. Min Act: -0.0001

Data Index: 1355194 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2826. Min Act: -0.0000

Data Index: 123612 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2528. Min Act: -0.0001

Data Index: 1536591 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1106273 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.4219. Min Range: -0.4219

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1440477 (Python Code)

Max Activating Token Index: 657