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

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

Neuron 2648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3912. Min Act: -0.0000

Data Index: 572629 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3562. Min Act: -0.0000

Data Index: 438920 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3612. Min Act: -0.0001

Data Index: 1059360 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3514. Min Act: -0.0000

Data Index: 872783 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3422. Min Act: -0.0000

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3332. Min Act: -0.0001

Data Index: 396250 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3360. Min Act: -0.0000

Data Index: 933909 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1009435 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3052. Min Act: -0.0000

Data Index: 784567 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3127. Min Act: -0.0001

Data Index: 1045726 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3010. Min Act: -0.0001

Data Index: 268810 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3121. Min Act: -0.0000

Data Index: 439070 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1160276 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3065. Min Act: -0.0001

Data Index: 1009702 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.3004. Min Act: -0.0000

Data Index: 500674 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.2987. Min Act: -0.0001

Data Index: 674592 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.2952. Min Act: -0.0001

Data Index: 469631 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.2968. Min Act: -0.0000

Data Index: 929595 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.2930. Min Act: -0.0001

Data Index: 789733 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.3912. Min Range: -0.3912

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1156173 (C4 (Web Text))

Max Activating Token Index: 907