Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3514 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6721. Min Act: -0.0001

Data Index: 828744 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6060. Min Act: -0.0001

Data Index: 406230 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6244. Min Act: -0.0001

Data Index: 236871 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5952. Min Act: -0.0001

Data Index: 915257 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6155. Min Act: -0.0001

Data Index: 218042 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5773. Min Act: -0.0001

Data Index: 633457 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5590. Min Act: -0.0001

Data Index: 1026924 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5844. Min Act: -0.0001

Data Index: 1113106 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5775. Min Act: -0.0001

Data Index: 1353300 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5555. Min Act: -0.0001

Data Index: 1102566 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1153308 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5476. Min Act: -0.0001

Data Index: 1083266 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5543. Min Act: -0.0001

Data Index: 616752 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5423. Min Act: -0.0001

Data Index: 1164615 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5208. Min Act: -0.0001

Data Index: 326757 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.4610. Min Act: -0.0001

Data Index: 255773 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1059540 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.4992. Min Act: -0.0001

Data Index: 605213 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5325. Min Act: -0.0001

Data Index: 36740 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.4603. Min Act: -0.0001

Data Index: 1145923 (C4 (Web Text))

Max Activating Token Index: 509