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

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

Neuron 2766 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3933. Min Act: -0.0001

Data Index: 567166 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.4724. Min Act: -0.0001

Data Index: 948343 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.4661. Min Act: -0.0001

Data Index: 689786 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.4870. Min Act: -0.0001

Data Index: 531556 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3884. Min Act: -0.0001

Data Index: 540803 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3440. Min Act: -0.0001

Data Index: 389606 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.2308. Min Act: -0.0001

Data Index: 998138 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.2913. Min Act: -0.0001

Data Index: 641078 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3608. Min Act: -0.0001

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3060. Min Act: -0.0001

Data Index: 1058518 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.2992. Min Act: -0.0001

Data Index: 244726 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3308. Min Act: -0.0001

Data Index: 1056553 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3890. Min Act: -0.0001

Data Index: 1089720 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.2354. Min Act: -0.0001

Data Index: 570476 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3273. Min Act: -0.0001

Data Index: 591126 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.1771. Min Act: -0.0001

Data Index: 555811 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.2960. Min Act: -0.0001

Data Index: 81598 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3213. Min Act: -0.0001

Data Index: 1255626 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.2479. Min Act: -0.0001

Data Index: 18007 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.4870. Min Range: -1.4870

Max Act: 1.3243. Min Act: -0.0001

Data Index: 295968 (C4 (Web Text))

Max Activating Token Index: 779