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

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

Neuron 770 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: 1.6197. Min Range: -1.6197

Max Act: 1.6197. Min Act: -0.0001

Data Index: 135677 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.4592. Min Act: -0.0001

Data Index: 227234 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.4041. Min Act: -0.0001

Data Index: 789000 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.3968. Min Act: -0.0001

Data Index: 550837 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.3093. Min Act: -0.0001

Data Index: 319015 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.4062. Min Act: -0.0001

Data Index: 869642 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.3227. Min Act: -0.0001

Data Index: 186094 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2801. Min Act: -0.0001

Data Index: 1119733 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2525. Min Act: -0.0001

Data Index: 2991 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.3309. Min Act: -0.0001

Data Index: 678268 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2765. Min Act: -0.0001

Data Index: 1192258 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.3162. Min Act: -0.0001

Data Index: 946576 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.3057. Min Act: -0.0001

Data Index: 699295 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2632. Min Act: -0.0001

Data Index: 6412 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2502. Min Act: -0.0001

Data Index: 972148 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2370. Min Act: -0.0001

Data Index: 583417 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2737. Min Act: -0.0001

Data Index: 104843 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2798. Min Act: -0.0001

Data Index: 1066649 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2715. Min Act: -0.0001

Data Index: 331857 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 1.6197. Min Range: -1.6197

Max Act: 1.2574. Min Act: -0.0001

Data Index: 1334387 (C4 (Web Text))

Max Activating Token Index: 1021