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

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

Neuron 338 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0028. Min Range: -1.0028

Max Act: 1.0028. Min Act: -0.0001

Data Index: 152166 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9469. Min Act: -0.0001

Data Index: 850758 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9610. Min Act: -0.0001

Data Index: 1244247 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9463. Min Act: -0.0001

Data Index: 1212936 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8632. Min Act: -0.0001

Data Index: 515290 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1133069 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8204. Min Act: -0.0001

Data Index: 358170 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8078. Min Act: -0.0001

Data Index: 1201405 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7741. Min Act: -0.0001

Data Index: 665532 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8464. Min Act: -0.0001

Data Index: 1239375 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8758. Min Act: -0.0001

Data Index: 5368 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7834. Min Act: -0.0001

Data Index: 367757 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7733. Min Act: -0.0001

Data Index: 1059349 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7915. Min Act: -0.0001

Data Index: 1046161 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7893. Min Act: -0.0001

Data Index: 1357592 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7907. Min Act: -0.0001

Data Index: 877949 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7443. Min Act: -0.0001

Data Index: 60943 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7444. Min Act: -0.0001

Data Index: 281960 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8031. Min Act: -0.0001

Data Index: 314833 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7401. Min Act: -0.0001

Data Index: 402587 (C4 (Web Text))

Max Activating Token Index: 817