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

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

Neuron 3264 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: 3.0579. Min Range: -3.0579

Max Act: 2.9673. Min Act: -0.0001

Data Index: 189591 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 3.0579. Min Range: -3.0579

Max Act: 3.0579. Min Act: -0.0001

Data Index: 1321975 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.9069. Min Act: -0.0001

Data Index: 948367 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.6783. Min Act: -0.0001

Data Index: 1147866 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.6780. Min Act: -0.0001

Data Index: 1291007 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.7587. Min Act: -0.0001

Data Index: 1219973 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.8834. Min Act: -0.0001

Data Index: 557791 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.5535. Min Act: -0.0001

Data Index: 656467 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.6456. Min Act: -0.0001

Data Index: 517698 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.7495. Min Act: -0.0001

Data Index: 1271143 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.4541. Min Act: -0.0001

Data Index: 1171852 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.7041. Min Act: -0.0001

Data Index: 872003 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.5715. Min Act: -0.0001

Data Index: 895814 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.6737. Min Act: -0.0001

Data Index: 1231127 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.2741. Min Act: -0.0001

Data Index: 235596 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.3939. Min Act: -0.0001

Data Index: 1093048 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.4995. Min Act: -0.0001

Data Index: 493647 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.3844. Min Act: -0.0001

Data Index: 457901 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.4856. Min Act: -0.0001

Data Index: 896385 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 3.0579. Min Range: -3.0579

Max Act: 2.2554. Min Act: -0.0001

Data Index: 719497 (C4 (Web Text))

Max Activating Token Index: 810