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

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

Neuron 4016 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: 0.5534. Min Range: -0.5534

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1144551 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5450. Min Act: -0.0000

Data Index: 90192 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5355. Min Act: -0.0001

Data Index: 418908 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4507. Min Act: -0.0001

Data Index: 1189753 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3587. Min Act: -0.0001

Data Index: 110479 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3375. Min Act: -0.0000

Data Index: 555305 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3320. Min Act: -0.0001

Data Index: 25727 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3181. Min Act: -0.0001

Data Index: 508803 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3246. Min Act: -0.0000

Data Index: 767649 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1209511 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3005. Min Act: -0.0001

Data Index: 1536476 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1017476 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2824. Min Act: -0.0001

Data Index: 1100641 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2905. Min Act: -0.0000

Data Index: 513448 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2890. Min Act: -0.0000

Data Index: 700980 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2892. Min Act: -0.0001

Data Index: 557062 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2851. Min Act: -0.0000

Data Index: 937305 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2745. Min Act: -0.0001

Data Index: 265504 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2597. Min Act: -0.0001

Data Index: 1306684 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1138456 (C4 (Web Text))

Max Activating Token Index: 753