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

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

Neuron 2030 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: 4.3131. Min Range: -4.3131

Max Act: 4.3131. Min Act: -0.0000

Data Index: 259191 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.5863. Min Act: -0.0000

Data Index: 440841 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.9522. Min Act: -0.0000

Data Index: 740988 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.8764. Min Act: -0.0001

Data Index: 1005848 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.5535. Min Act: -0.0000

Data Index: 685854 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.9522. Min Act: -0.0000

Data Index: 1076628 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.6154. Min Act: -0.0000

Data Index: 1081984 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.5480. Min Act: -0.0000

Data Index: 1211227 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.6477. Min Act: -0.0000

Data Index: 67755 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 4.3131. Min Range: -4.3131

Max Act: 4.1522. Min Act: -0.0001

Data Index: 642835 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.6641. Min Act: -0.0000

Data Index: 111464 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.3586. Min Act: -0.0000

Data Index: 249267 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.1093. Min Act: -0.0000

Data Index: 794541 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 4.3131. Min Range: -4.3131

Max Act: 2.8662. Min Act: -0.0000

Data Index: 206177 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 4.3131. Min Range: -4.3131

Max Act: 2.9823. Min Act: -0.0000

Data Index: 381856 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 4.3131. Min Range: -4.3131

Max Act: 2.9117. Min Act: -0.0000

Data Index: 459562 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 4.3131. Min Range: -4.3131

Max Act: 3.3041. Min Act: -0.0000

Data Index: 99822 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 4.3131. Min Range: -4.3131

Max Act: 2.9264. Min Act: -0.0000

Data Index: 1219116 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 4.3131. Min Range: -4.3131

Max Act: 2.7361. Min Act: -0.0000

Data Index: 374925 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 4.3131. Min Range: -4.3131

Max Act: 2.6550. Min Act: -0.0000

Data Index: 239094 (C4 (Web Text))

Max Activating Token Index: 134