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

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

Neuron 9 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7926. Min Act: -0.0001

Data Index: 382584 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7830. Min Act: -0.0001

Data Index: 560034 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7925. Min Act: -0.0001

Data Index: 931198 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7072. Min Act: -0.0001

Data Index: 1278216 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7161. Min Act: -0.0001

Data Index: 1222769 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6922. Min Act: -0.0001

Data Index: 524861 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7049. Min Act: -0.0001

Data Index: 1321983 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6341. Min Act: -0.0001

Data Index: 596528 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6522. Min Act: -0.0001

Data Index: 726131 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6287. Min Act: -0.0001

Data Index: 648040 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6646. Min Act: -0.0001

Data Index: 848869 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6404. Min Act: -0.0001

Data Index: 493783 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6413. Min Act: -0.0001

Data Index: 501158 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6160. Min Act: -0.0001

Data Index: 343576 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6347. Min Act: -0.0001

Data Index: 1015113 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6177. Min Act: -0.0001

Data Index: 731243 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6397. Min Act: -0.0001

Data Index: 967470 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5973. Min Act: -0.0001

Data Index: 696604 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6105. Min Act: -0.0001

Data Index: 875564 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5847. Min Act: -0.0001

Data Index: 1055 (C4 (Web Text))

Max Activating Token Index: 760