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

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

Neuron 1995 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: 1.7343. Min Range: -1.7343

Max Act: 1.7343. Min Act: -0.0000

Data Index: 1150387 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.3134. Min Act: -0.0000

Data Index: 557517 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2273. Min Act: -0.0001

Data Index: 1282358 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1145128 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1291. Min Act: -0.0000

Data Index: 492084 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.1211. Min Act: -0.0000

Data Index: 90608 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.0852. Min Act: -0.0001

Data Index: 1132055 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.0670. Min Act: -0.0001

Data Index: 105342 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.0587. Min Act: -0.0000

Data Index: 599811 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9654. Min Act: -0.0000

Data Index: 912574 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9943. Min Act: -0.0001

Data Index: 276235 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9715. Min Act: -0.0001

Data Index: 398023 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9866. Min Act: -0.0000

Data Index: 162391 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.7343. Min Range: -1.7343

Max Act: 1.0163. Min Act: -0.0000

Data Index: 261191 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9088. Min Act: -0.0000

Data Index: 470745 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.8648. Min Act: -0.0001

Data Index: 1266927 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9421. Min Act: -0.0000

Data Index: 547212 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9028. Min Act: -0.0000

Data Index: 505564 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.9100. Min Act: -0.0000

Data Index: 711959 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 1.7343. Min Range: -1.7343

Max Act: 0.8316. Min Act: -0.0000

Data Index: 179654 (C4 (Web Text))

Max Activating Token Index: 595