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

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

Neuron 4379 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0724. Min Range: -3.0724

Max Act: 3.0025. Min Act: -0.0000

Data Index: 253095 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.9837. Min Act: -0.0000

Data Index: 195354 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 3.0724. Min Range: -3.0724

Max Act: 3.0724. Min Act: -0.0000

Data Index: 591076 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.6983. Min Act: -0.0000

Data Index: 336473 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.0435. Min Act: -0.0000

Data Index: 187759 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.5979. Min Act: -0.0000

Data Index: 521899 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.2999. Min Act: -0.0000

Data Index: 171552 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.5540. Min Act: -0.0000

Data Index: 54072 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.3500. Min Act: -0.0000

Data Index: 148192 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.3563. Min Act: -0.0000

Data Index: 423047 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.3182. Min Act: -0.0000

Data Index: 1337484 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.4213. Min Act: -0.0000

Data Index: 674358 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.3015. Min Act: -0.0000

Data Index: 156550 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.3666. Min Act: -0.0000

Data Index: 849529 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.3439. Min Act: -0.0000

Data Index: 577721 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.1830. Min Act: -0.0000

Data Index: 1154259 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.0575. Min Act: -0.0000

Data Index: 399569 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.4387. Min Act: -0.0000

Data Index: 1165 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.0363. Min Act: -0.0000

Data Index: 977080 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 3.0724. Min Range: -3.0724

Max Act: 2.2519. Min Act: -0.0000

Data Index: 627972 (C4 (Web Text))

Max Activating Token Index: 427