Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.5257. Min Act: -0.0001

Data Index: 727541 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4736. Min Act: -0.0001

Data Index: 99015 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4775. Min Act: -0.0001

Data Index: 702043 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4357. Min Act: -0.0001

Data Index: 1285064 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4196. Min Act: -0.0001

Data Index: 614097 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4138. Min Act: -0.0001

Data Index: 973857 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4181. Min Act: -0.0001

Data Index: 164375 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4109. Min Act: -0.0001

Data Index: 207538 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3954. Min Act: -0.0001

Data Index: 1218903 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4214. Min Act: -0.0001

Data Index: 596825 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1213015 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3990. Min Act: -0.0001

Data Index: 358594 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3837. Min Act: -0.0001

Data Index: 1232959 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3813. Min Act: -0.0001

Data Index: 690277 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.4165. Min Act: -0.0001

Data Index: 1272897 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3898. Min Act: -0.0001

Data Index: 1043653 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3959. Min Act: -0.0001

Data Index: 448217 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3775. Min Act: -0.0001

Data Index: 934919 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3761. Min Act: -0.0001

Data Index: 853291 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.5257. Min Range: -0.5257

Max Act: 0.3859. Min Act: -0.0001

Data Index: 258610 (C4 (Web Text))

Max Activating Token Index: 426