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

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

Neuron 5713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8500. Min Range: -4.8500

Max Act: 4.8500. Min Act: -0.0000

Data Index: 786936 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 4.8500. Min Range: -4.8500

Max Act: 4.3293. Min Act: -0.0000

Data Index: 619916 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 4.8500. Min Range: -4.8500

Max Act: 4.3229. Min Act: -0.0000

Data Index: 1349110 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.9293. Min Act: -0.0000

Data Index: 990903 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 4.8500. Min Range: -4.8500

Max Act: 4.0319. Min Act: -0.0000

Data Index: 286633 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.9887. Min Act: -0.0000

Data Index: 416204 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.9526. Min Act: -0.0000

Data Index: 690253 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.7407. Min Act: -0.0000

Data Index: 281696 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.8632. Min Act: -0.0000

Data Index: 306058 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.6079. Min Act: -0.0000

Data Index: 264195 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.7358. Min Act: -0.0000

Data Index: 637334 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.7276. Min Act: -0.0000

Data Index: 1098700 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.5604. Min Act: -0.0000

Data Index: 54499 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.5058. Min Act: -0.0000

Data Index: 561303 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.6708. Min Act: -0.0000

Data Index: 673511 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.6342. Min Act: -0.0000

Data Index: 873818 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.4892. Min Act: -0.0000

Data Index: 417228 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.6119. Min Act: -0.0000

Data Index: 952850 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.6133. Min Act: -0.0000

Data Index: 263919 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 4.8500. Min Range: -4.8500

Max Act: 3.7528. Min Act: -0.0000

Data Index: 1349444 (C4 (Web Text))

Max Activating Token Index: 216