Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 868 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4932. Min Act: -0.0001

Data Index: 1331939 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4908. Min Act: -0.0001

Data Index: 1288686 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4843. Min Act: -0.0001

Data Index: 461499 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4397. Min Act: -0.0001

Data Index: 1079358 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4695. Min Act: -0.0001

Data Index: 56675 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4422. Min Act: -0.0001

Data Index: 874067 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4341. Min Act: -0.0001

Data Index: 505881 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4330. Min Act: -0.0001

Data Index: 478611 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4125. Min Act: -0.0001

Data Index: 877097 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4214. Min Act: -0.0001

Data Index: 780243 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4050. Min Act: -0.0001

Data Index: 394846 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3984. Min Act: -0.0001

Data Index: 732767 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4034. Min Act: -0.0001

Data Index: 748943 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3742. Min Act: -0.0001

Data Index: 1134268 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3987. Min Act: -0.0001

Data Index: 620484 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3762. Min Act: -0.0001

Data Index: 760954 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3963. Min Act: -0.0001

Data Index: 1192600 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3820. Min Act: -0.0001

Data Index: 1113950 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3676. Min Act: -0.0001

Data Index: 1253146 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3538. Min Act: -0.0001

Data Index: 599443 (C4 (Web Text))

Max Activating Token Index: 675