Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 570 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.3950. Min Act: -0.0000

Data Index: 1061014 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.8948. Min Act: -0.0000

Data Index: 1146464 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.0188. Min Act: -0.0000

Data Index: 901447 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.9240. Min Act: -0.0000

Data Index: 1163487 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.5893. Min Act: -0.0000

Data Index: 581547 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.6819. Min Act: -0.0000

Data Index: 1217530 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.6191. Min Act: -0.0000

Data Index: 221803 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.6475. Min Act: -0.0000

Data Index: 1038882 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.4953. Min Act: -0.0000

Data Index: 1200601 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.4436. Min Act: -0.0000

Data Index: 879484 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1182897 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.4183. Min Act: -0.0000

Data Index: 493174 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1017085 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.2610. Min Act: -0.0000

Data Index: 494370 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.3706. Min Act: -0.0000

Data Index: 932547 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.3785. Min Act: -0.0000

Data Index: 127129 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.3758. Min Act: -0.0000

Data Index: 813279 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.4967. Min Act: -0.0000

Data Index: 1124609 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.3520. Min Act: -0.0000

Data Index: 634472 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 3.3950. Min Range: -3.3950

Max Act: 2.3021. Min Act: -0.0000

Data Index: 244030 (C4 (Web Text))

Max Activating Token Index: 1015