Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 972 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.9135. Min Act: -0.0003

Data Index: 284757 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 1.0163. Min Range: -1.0163

Max Act: 1.0163. Min Act: -0.0003

Data Index: 457518 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.9891. Min Act: -0.0003

Data Index: 371265 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.8479. Min Act: -0.0003

Data Index: 887030 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.7933. Min Act: -0.0003

Data Index: 1022919 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.7091. Min Act: -0.0003

Data Index: 35457 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.7031. Min Act: -0.0003

Data Index: 724458 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6605. Min Act: -0.0002

Data Index: 1308008 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6683. Min Act: -0.0003

Data Index: 1037556 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6562. Min Act: -0.0003

Data Index: 1202414 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6545. Min Act: -0.0003

Data Index: 953299 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6476. Min Act: -0.0003

Data Index: 875361 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6828. Min Act: -0.0003

Data Index: 1143372 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6185. Min Act: -0.0003

Data Index: 248011 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6598. Min Act: -0.0003

Data Index: 738246 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6706. Min Act: -0.0003

Data Index: 748262 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.5842. Min Act: -0.0003

Data Index: 715119 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6018. Min Act: -0.0003

Data Index: 368763 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6391. Min Act: -0.0003

Data Index: 211669 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.0163. Min Range: -1.0163

Max Act: 0.6506. Min Act: -0.0003

Data Index: 644228 (C4 (Web Text))

Max Activating Token Index: 919