Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3297 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.2819. Min Act: -0.0000

Data Index: 232809 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.2106. Min Act: -0.0001

Data Index: 307784 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.2715. Min Act: -0.0001

Data Index: 1497269 (Python Code)

Max Activating Token Index: 1005

Text #3

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.2170. Min Act: -0.0000

Data Index: 699014 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.2473. Min Act: -0.0001

Data Index: 677900 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1356432 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1325. Min Act: -0.0001

Data Index: 31827 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1790. Min Act: -0.0001

Data Index: 651788 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1325. Min Act: -0.0001

Data Index: 354591 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.0941. Min Act: -0.0001

Data Index: 868948 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.0108. Min Act: -0.0001

Data Index: 407437 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.2520. Min Act: -0.0001

Data Index: 382154 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1259354 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1059. Min Act: -0.0001

Data Index: 829393 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1458886 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1269. Min Act: -0.0000

Data Index: 943118 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.2819. Min Range: -1.2819

Max Act: 0.9678. Min Act: -0.0001

Data Index: 487555 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1075128 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1061999 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.2819. Min Range: -1.2819

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1047924 (C4 (Web Text))

Max Activating Token Index: 538