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

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

Neuron 3881 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9697. Min Act: -0.0002

Data Index: 1085491 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9332. Min Act: -0.0002

Data Index: 1014039 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9232. Min Act: -0.0002

Data Index: 1008519 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8852. Min Act: -0.0002

Data Index: 1349555 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9109. Min Act: -0.0002

Data Index: 196144 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8894. Min Act: -0.0001

Data Index: 1237658 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9129. Min Act: -0.0002

Data Index: 63558 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8966. Min Act: -0.0002

Data Index: 297180 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8904. Min Act: -0.0002

Data Index: 855962 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8299. Min Act: -0.0002

Data Index: 1002952 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8462. Min Act: -0.0002

Data Index: 897005 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8749. Min Act: -0.0002

Data Index: 455719 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8407. Min Act: -0.0002

Data Index: 1322952 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8969. Min Act: -0.0001

Data Index: 316237 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8910. Min Act: -0.0002

Data Index: 257734 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7785. Min Act: -0.0002

Data Index: 856217 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8802. Min Act: -0.0002

Data Index: 362599 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8539. Min Act: -0.0002

Data Index: 164627 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8535. Min Act: -0.0002

Data Index: 725306 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8261. Min Act: -0.0002

Data Index: 1229438 (C4 (Web Text))

Max Activating Token Index: 583