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

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

Neuron 3925 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5864. Min Act: -0.0000

Data Index: 467504 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.6041. Min Act: -0.0000

Data Index: 580107 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.6101. Min Act: -0.0000

Data Index: 445546 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5860. Min Act: -0.0001

Data Index: 674320 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1036155 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5351. Min Act: -0.0001

Data Index: 1175547 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5209. Min Act: -0.0000

Data Index: 948447 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4913. Min Act: -0.0001

Data Index: 271704 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4721. Min Act: -0.0001

Data Index: 19177 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1170203 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4777. Min Act: -0.0001

Data Index: 977738 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1083822 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4661. Min Act: -0.0000

Data Index: 363195 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4672. Min Act: -0.0001

Data Index: 286193 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4618. Min Act: -0.0000

Data Index: 336246 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4464. Min Act: -0.0000

Data Index: 415659 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1093067 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1106680 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1027928 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4486. Min Act: -0.0001

Data Index: 433272 (C4 (Web Text))

Max Activating Token Index: 242