Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5081 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.2669. Min Act: -0.0000

Data Index: 165420 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0483. Min Act: -0.0000

Data Index: 397634 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1263072 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0071. Min Act: -0.0000

Data Index: 239916 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.2669. Min Range: -1.2669

Max Act: 1.0052. Min Act: -0.0000

Data Index: 771576 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1186577 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.7992. Min Act: -0.0000

Data Index: 714720 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.7198. Min Act: -0.0000

Data Index: 125952 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.7124. Min Act: -0.0000

Data Index: 139631 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.7153. Min Act: -0.0000

Data Index: 223253 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1055788 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6405. Min Act: -0.0000

Data Index: 342265 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6591. Min Act: -0.0000

Data Index: 185407 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6965. Min Act: -0.0000

Data Index: 33404 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6034. Min Act: -0.0000

Data Index: 866546 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6519. Min Act: -0.0000

Data Index: 568979 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6612. Min Act: -0.0000

Data Index: 268625 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1043807 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6194. Min Act: -0.0000

Data Index: 573882 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 1.2669. Min Range: -1.2669

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1110636 (C4 (Web Text))

Max Activating Token Index: 237