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

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

Neuron 2551 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: 3.1678. Min Range: -3.1678

Max Act: 3.0574. Min Act: -0.0001

Data Index: 663185 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.1678. Min Range: -3.1678

Max Act: 3.1678. Min Act: -0.0001

Data Index: 1257836 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.8162. Min Act: -0.0001

Data Index: 296584 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.9709. Min Act: -0.0001

Data Index: 66119 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.8652. Min Act: -0.0001

Data Index: 1085493 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.7489. Min Act: -0.0001

Data Index: 330221 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.4341. Min Act: -0.0001

Data Index: 278351 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.3214. Min Act: -0.0001

Data Index: 455881 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.5170. Min Act: -0.0001

Data Index: 1218456 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.4299. Min Act: -0.0001

Data Index: 177494 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.3988. Min Act: -0.0001

Data Index: 1180114 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.3640. Min Act: -0.0001

Data Index: 1082917 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.3572. Min Act: -0.0001

Data Index: 175474 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.4542. Min Act: -0.0001

Data Index: 771769 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.2249. Min Act: -0.0001

Data Index: 1100664 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.1951. Min Act: -0.0001

Data Index: 1101722 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.2645. Min Act: -0.0001

Data Index: 157742 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.2879. Min Act: -0.0001

Data Index: 1147219 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.1444. Min Act: -0.0001

Data Index: 323064 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 3.1678. Min Range: -3.1678

Max Act: 2.2845. Min Act: -0.0001

Data Index: 598717 (C4 (Web Text))

Max Activating Token Index: 92