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

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

Neuron 2952 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0001

Data Index: 463501 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1623. Min Act: -0.0001

Data Index: 119605 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1140032 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1205109 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1194. Min Act: -0.0001

Data Index: 967930 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1324750 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1146312 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1078. Min Act: -0.0001

Data Index: 507664 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1076. Min Act: -0.0001

Data Index: 323899 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1038. Min Act: -0.0001

Data Index: 80933 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.0974. Min Act: -0.0001

Data Index: 525897 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1125. Min Act: -0.0001

Data Index: 498880 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1058982 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1017. Min Act: -0.0001

Data Index: 71346 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.0986. Min Act: -0.0001

Data Index: 896282 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1067. Min Act: -0.0001

Data Index: 117101 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1015. Min Act: -0.0001

Data Index: 984069 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.0967. Min Act: -0.0001

Data Index: 506111 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.0954. Min Act: -0.0001

Data Index: 545430 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.0956. Min Act: -0.0001

Data Index: 813251 (C4 (Web Text))

Max Activating Token Index: 920