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

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

Neuron 3002 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3908. Min Act: -0.0001

Data Index: 825919 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3715. Min Act: -0.0000

Data Index: 701789 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3330. Min Act: -0.0000

Data Index: 351476 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3387. Min Act: -0.0001

Data Index: 893913 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3126. Min Act: -0.0001

Data Index: 945235 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2897. Min Act: -0.0001

Data Index: 87470 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2749. Min Act: -0.0000

Data Index: 613995 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2818. Min Act: -0.0000

Data Index: 15087 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2607. Min Act: -0.0001

Data Index: 937814 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2688. Min Act: -0.0001

Data Index: 716792 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2624. Min Act: -0.0001

Data Index: 258183 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2592. Min Act: -0.0001

Data Index: 1153756 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2836. Min Act: -0.0000

Data Index: 35238 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1049557 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2509. Min Act: -0.0001

Data Index: 501188 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2379. Min Act: -0.0000

Data Index: 367412 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1205752 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1305354 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2476. Min Act: -0.0001

Data Index: 94662 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2233. Min Act: -0.0000

Data Index: 564637 (C4 (Web Text))

Max Activating Token Index: 971