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

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

Neuron 694 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: 0.9118. Min Range: -0.9118

Max Act: 0.9118. Min Act: -0.0001

Data Index: 1089019 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.8177. Min Act: -0.0001

Data Index: 1247029 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.6471. Min Act: -0.0001

Data Index: 1318704 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1340420 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1274091 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4102. Min Act: -0.0001

Data Index: 484270 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4190. Min Act: -0.0000

Data Index: 124201 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4192. Min Act: -0.0001

Data Index: 544680 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4038. Min Act: -0.0001

Data Index: 113756 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4159. Min Act: -0.0001

Data Index: 232992 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3891. Min Act: -0.0001

Data Index: 116616 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.4095. Min Act: -0.0000

Data Index: 257512 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3936. Min Act: -0.0001

Data Index: 1246861 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3907. Min Act: -0.0000

Data Index: 88319 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1299028 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1325253 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1208791 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3744. Min Act: -0.0000

Data Index: 416320 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3605. Min Act: -0.0001

Data Index: 223169 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.3663. Min Act: -0.0000

Data Index: 77828 (C4 (Web Text))

Max Activating Token Index: 25