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

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

Neuron 451 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: 8.2997. Min Range: -8.2997

Max Act: 8.2997. Min Act: -0.0001

Data Index: 372075 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 8.2997. Min Range: -8.2997

Max Act: 7.4237. Min Act: -0.0001

Data Index: 29452 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 8.2997. Min Range: -8.2997

Max Act: 7.2830. Min Act: -0.0001

Data Index: 634289 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 8.2997. Min Range: -8.2997

Max Act: 7.5862. Min Act: -0.0001

Data Index: 975318 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 8.2997. Min Range: -8.2997

Max Act: 7.0241. Min Act: -0.0001

Data Index: 758609 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 8.2997. Min Range: -8.2997

Max Act: 7.0034. Min Act: -0.0001

Data Index: 1296002 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 8.2997. Min Range: -8.2997

Max Act: 6.7462. Min Act: -0.0001

Data Index: 1208337 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 8.2997. Min Range: -8.2997

Max Act: 6.4492. Min Act: -0.0001

Data Index: 1140939 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 8.2997. Min Range: -8.2997

Max Act: 6.2471. Min Act: -0.0001

Data Index: 245862 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 8.2997. Min Range: -8.2997

Max Act: 6.1009. Min Act: -0.0001

Data Index: 458723 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.9617. Min Act: -0.0001

Data Index: 146036 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.8332. Min Act: -0.0001

Data Index: 749342 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.9386. Min Act: -0.0001

Data Index: 157527 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.5781. Min Act: -0.0001

Data Index: 1127647 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.8477. Min Act: -0.0001

Data Index: 483797 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.4697. Min Act: -0.0001

Data Index: 749270 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.7972. Min Act: -0.0001

Data Index: 1143529 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.4476. Min Act: -0.0001

Data Index: 1353666 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.2443. Min Act: -0.0001

Data Index: 460081 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 8.2997. Min Range: -8.2997

Max Act: 5.3951. Min Act: -0.0001

Data Index: 237790 (C4 (Web Text))

Max Activating Token Index: 69