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

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

Neuron 3289 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.3690. Min Act: -0.0001

Data Index: 171022 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.4853. Min Act: -0.0001

Data Index: 1010360 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.3263. Min Act: -0.0001

Data Index: 798312 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.5580. Min Act: -0.0001

Data Index: 1014175 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.2385. Min Act: -0.0001

Data Index: 992931 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.0717. Min Act: -0.0001

Data Index: 1218786 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.2994. Min Act: -0.0001

Data Index: 158226 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.3943. Min Act: -0.0001

Data Index: 1135776 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.2618. Min Act: -0.0001

Data Index: 866607 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.3964. Min Act: -0.0001

Data Index: 1244706 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.0994. Min Act: -0.0001

Data Index: 1015464 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.2045. Min Act: -0.0001

Data Index: 438097 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.2078. Min Act: -0.0001

Data Index: 99982 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.3361. Min Act: -0.0001

Data Index: 681996 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.3275. Min Act: -0.0001

Data Index: 1120741 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.1761. Min Act: -0.0001

Data Index: 322952 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.0345. Min Act: -0.0001

Data Index: 591147 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.0012. Min Act: -0.0001

Data Index: 858985 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.1396. Min Act: -0.0001

Data Index: 1130984 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 3.5580. Min Range: -3.5580

Max Act: 3.2655. Min Act: -0.0001

Data Index: 198210 (C4 (Web Text))

Max Activating Token Index: 338