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

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

Neuron 1903 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.5854. Min Act: -0.0001

Data Index: 92051 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1095198 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4643. Min Act: -0.0000

Data Index: 891207 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4589. Min Act: -0.0000

Data Index: 791738 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4675. Min Act: -0.0001

Data Index: 914117 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3794. Min Act: -0.0001

Data Index: 652392 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3871. Min Act: -0.0001

Data Index: 112482 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4479. Min Act: -0.0001

Data Index: 1000996 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1634878 (Python Code)

Max Activating Token Index: 523

Text #9

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1262720 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4062. Min Act: -0.0000

Data Index: 134273 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3460. Min Act: -0.0000

Data Index: 811907 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1100806 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3948. Min Act: -0.0000

Data Index: 680748 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3655. Min Act: -0.0001

Data Index: 1181796 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3574. Min Act: -0.0000

Data Index: 481991 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3713. Min Act: -0.0001

Data Index: 34210 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3695. Min Act: -0.0000

Data Index: 915711 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1267944 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3011. Min Act: -0.0000

Data Index: 154249 (C4 (Web Text))

Max Activating Token Index: 754