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

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

Neuron 3618 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9006. Min Act: -0.0001

Data Index: 767200 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8593. Min Act: -0.0001

Data Index: 592503 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8061. Min Act: -0.0001

Data Index: 969232 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9409. Min Act: -0.0001

Data Index: 364391 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 4.0096. Min Range: -4.0096

Max Act: 4.0096. Min Act: -0.0001

Data Index: 1341125 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9955. Min Act: -0.0001

Data Index: 652539 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8029. Min Act: -0.0001

Data Index: 126211 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8417. Min Act: -0.0001

Data Index: 783036 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.7877. Min Act: -0.0001

Data Index: 125635 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.4474. Min Act: -0.0001

Data Index: 1157441 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.5869. Min Act: -0.0001

Data Index: 1353896 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3927. Min Act: -0.0001

Data Index: 570828 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3036. Min Act: -0.0001

Data Index: 1282367 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.5841. Min Act: -0.0001

Data Index: 212230 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3990. Min Act: -0.0001

Data Index: 714785 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3848. Min Act: -0.0001

Data Index: 45872 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3385. Min Act: -0.0001

Data Index: 226498 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3592. Min Act: -0.0001

Data Index: 50300 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.3171. Min Act: -0.0001

Data Index: 54576 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.4275. Min Act: -0.0001

Data Index: 39348 (C4 (Web Text))

Max Activating Token Index: 776