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

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

Neuron 1153 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3778. Min Act: -0.0003

Data Index: 511757 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3488. Min Act: -0.0003

Data Index: 1124132 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3718. Min Act: -0.0003

Data Index: 950633 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3653. Min Act: -0.0003

Data Index: 199765 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3620. Min Act: -0.0003

Data Index: 1306618 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3580. Min Act: -0.0003

Data Index: 1025067 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3573. Min Act: -0.0003

Data Index: 794088 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3514. Min Act: -0.0003

Data Index: 998026 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3505. Min Act: -0.0003

Data Index: 179154 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3460. Min Act: -0.0003

Data Index: 1153002 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3175. Min Act: -0.0002

Data Index: 808411 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3178. Min Act: -0.0002

Data Index: 988504 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3345. Min Act: -0.0003

Data Index: 820019 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3331. Min Act: -0.0003

Data Index: 114843 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3311. Min Act: -0.0003

Data Index: 540498 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3245. Min Act: -0.0003

Data Index: 760560 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3248. Min Act: -0.0003

Data Index: 540859 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3243. Min Act: -0.0003

Data Index: 8996 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3202. Min Act: -0.0003

Data Index: 586926 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.3778. Min Range: -0.3778

Max Act: 0.3181. Min Act: -0.0002

Data Index: 1014976 (C4 (Web Text))

Max Activating Token Index: 749