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

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

Neuron 647 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.4106. Min Act: -0.0001

Data Index: 1052038 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3540. Min Act: -0.0001

Data Index: 435784 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3483. Min Act: -0.0000

Data Index: 435633 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3175. Min Act: -0.0000

Data Index: 891155 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3008. Min Act: -0.0000

Data Index: 5610 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3124. Min Act: -0.0000

Data Index: 100106 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2996. Min Act: -0.0000

Data Index: 946443 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3134. Min Act: -0.0001

Data Index: 75923 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2880. Min Act: -0.0000

Data Index: 932289 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2823. Min Act: -0.0001

Data Index: 810562 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2749. Min Act: -0.0001

Data Index: 133753 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1028020 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1027437 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2794. Min Act: -0.0001

Data Index: 511068 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2569. Min Act: -0.0001

Data Index: 481875 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1074564 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2526. Min Act: -0.0001

Data Index: 48892 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2446. Min Act: -0.0000

Data Index: 733299 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2523. Min Act: -0.0001

Data Index: 535205 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2329. Min Act: -0.0000

Data Index: 5694 (C4 (Web Text))

Max Activating Token Index: 121