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

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

Neuron 1431 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: 0.4895. Min Range: -0.4895

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1236667 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4895. Min Act: -0.0001

Data Index: 383930 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4337. Min Act: -0.0001

Data Index: 735199 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1058153 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4512. Min Act: -0.0001

Data Index: 401338 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4327. Min Act: -0.0001

Data Index: 15706 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4428. Min Act: -0.0001

Data Index: 325008 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4345. Min Act: -0.0001

Data Index: 983777 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4592. Min Act: -0.0001

Data Index: 965004 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3971. Min Act: -0.0001

Data Index: 185198 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4323. Min Act: -0.0001

Data Index: 3741 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4145. Min Act: -0.0001

Data Index: 532725 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4254. Min Act: -0.0001

Data Index: 121096 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4219. Min Act: -0.0001

Data Index: 324520 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3926. Min Act: -0.0001

Data Index: 753011 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4045. Min Act: -0.0001

Data Index: 976394 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4032. Min Act: -0.0001

Data Index: 246767 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4025. Min Act: -0.0001

Data Index: 1312235 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3990. Min Act: -0.0001

Data Index: 659682 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3978. Min Act: -0.0001

Data Index: 330930 (C4 (Web Text))

Max Activating Token Index: 508