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

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

Neuron 2720 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: 4.5567. Min Range: -4.5567

Max Act: 4.5567. Min Act: -0.0001

Data Index: 540209 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.9441. Min Act: -0.0001

Data Index: 776381 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.7127. Min Act: -0.0001

Data Index: 94100 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.6949. Min Act: -0.0001

Data Index: 624568 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.8152. Min Act: -0.0001

Data Index: 83424 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.7311. Min Act: -0.0001

Data Index: 792413 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.7010. Min Act: -0.0001

Data Index: 15224 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.4741. Min Act: -0.0001

Data Index: 884856 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.5754. Min Act: -0.0001

Data Index: 348902 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.5412. Min Act: -0.0001

Data Index: 149744 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.7048. Min Act: -0.0001

Data Index: 1314560 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.5303. Min Act: -0.0001

Data Index: 203331 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.3641. Min Act: -0.0000

Data Index: 1105346 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.3510. Min Act: -0.0001

Data Index: 1214531 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.3774. Min Act: -0.0001

Data Index: 22598 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.6199. Min Act: -0.0001

Data Index: 62812 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.6111. Min Act: -0.0001

Data Index: 320151 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.2994. Min Act: -0.0000

Data Index: 1113666 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.4185. Min Act: -0.0001

Data Index: 959511 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 4.5567. Min Range: -4.5567

Max Act: 3.4115. Min Act: -0.0001

Data Index: 15365 (C4 (Web Text))

Max Activating Token Index: 36