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

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

Neuron 3069 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1041935 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1043440 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.6665. Min Act: -0.0001

Data Index: 184111 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.6566. Min Act: -0.0001

Data Index: 1348183 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.6202. Min Act: -0.0000

Data Index: 938498 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.6159. Min Act: -0.0001

Data Index: 1162757 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5796. Min Act: -0.0001

Data Index: 30374 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5462. Min Act: -0.0001

Data Index: 1216230 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1086129 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5585. Min Act: -0.0001

Data Index: 162715 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5670. Min Act: -0.0001

Data Index: 1269529 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5538. Min Act: -0.0001

Data Index: 462149 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1253088 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5720. Min Act: -0.0001

Data Index: 1158283 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5316. Min Act: -0.0000

Data Index: 816270 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5423. Min Act: -0.0001

Data Index: 283527 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5365. Min Act: -0.0000

Data Index: 74700 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1000513 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5397. Min Act: -0.0000

Data Index: 448188 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.8044. Min Range: -0.8044

Max Act: 0.5394. Min Act: -0.0001

Data Index: 520651 (C4 (Web Text))

Max Activating Token Index: 160