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

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

Neuron 6081 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.5119. Min Act: -0.0000

Data Index: 217468 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1006938 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.1981. Min Act: -0.0000

Data Index: 642324 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.2896. Min Act: -0.0000

Data Index: 688299 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.2982. Min Act: -0.0001

Data Index: 1111880 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.1219. Min Act: -0.0000

Data Index: 698790 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.2343. Min Act: -0.0000

Data Index: 36425 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.1494. Min Act: -0.0000

Data Index: 466797 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.1556. Min Act: -0.0000

Data Index: 1230160 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.1080. Min Act: -0.0000

Data Index: 191819 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.1065. Min Act: -0.0000

Data Index: 965185 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.1217. Min Act: -0.0000

Data Index: 653744 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.0875. Min Act: -0.0000

Data Index: 353512 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.5119. Min Range: -1.5119

Max Act: 0.9144. Min Act: -0.0000

Data Index: 925781 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.0555. Min Act: -0.0000

Data Index: 549949 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.0171. Min Act: -0.0000

Data Index: 969290 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.0461. Min Act: -0.0000

Data Index: 279342 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.0205. Min Act: -0.0000

Data Index: 370565 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.0045. Min Act: -0.0000

Data Index: 37327 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 1.5119. Min Range: -1.5119

Max Act: 1.0203. Min Act: -0.0000

Data Index: 505467 (C4 (Web Text))

Max Activating Token Index: 7