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

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

Neuron 5927 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.6080. Min Act: -0.0000

Data Index: 172619 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1518. Min Act: -0.0000

Data Index: 1191809 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1968. Min Act: -0.0000

Data Index: 151675 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1217. Min Act: -0.0000

Data Index: 927810 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1005276 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2402. Min Act: -0.0000

Data Index: 462923 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0929. Min Act: -0.0000

Data Index: 549737 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0289. Min Act: -0.0000

Data Index: 697123 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1040881 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1173316 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0650. Min Act: -0.0000

Data Index: 991920 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.6080. Min Range: -1.6080

Max Act: 0.9765. Min Act: -0.0000

Data Index: 452562 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0315. Min Act: -0.0000

Data Index: 295773 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 1.6080. Min Range: -1.6080

Max Act: 0.9696. Min Act: -0.0000

Data Index: 837688 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0321. Min Act: -0.0000

Data Index: 661449 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0186. Min Act: -0.0000

Data Index: 591962 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0050. Min Act: -0.0000

Data Index: 13343 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.0494. Min Act: -0.0000

Data Index: 633276 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.6080. Min Range: -1.6080

Max Act: 0.9804. Min Act: -0.0000

Data Index: 611476 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 1.6080. Min Range: -1.6080

Max Act: 0.9810. Min Act: -0.0000

Data Index: 438421 (C4 (Web Text))

Max Activating Token Index: 60