Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4313 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.0131. Min Range: -6.0131

Max Act: 6.0131. Min Act: -0.0000

Data Index: 662852 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 6.0131. Min Range: -6.0131

Max Act: 5.1952. Min Act: -0.0000

Data Index: 661854 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 6.0131. Min Range: -6.0131

Max Act: 5.1359. Min Act: -0.0000

Data Index: 31311 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 6.0131. Min Range: -6.0131

Max Act: 5.1955. Min Act: -0.0000

Data Index: 245140 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 6.0131. Min Range: -6.0131

Max Act: 5.0833. Min Act: -0.0000

Data Index: 921876 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.8414. Min Act: -0.0000

Data Index: 630606 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.9604. Min Act: -0.0000

Data Index: 1107843 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.7546. Min Act: -0.0000

Data Index: 471073 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.5206. Min Act: -0.0000

Data Index: 415339 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.8818. Min Act: -0.0000

Data Index: 45545 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.5060. Min Act: -0.0000

Data Index: 594442 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.5237. Min Act: -0.0000

Data Index: 1340375 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.5093. Min Act: -0.0000

Data Index: 693178 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.5124. Min Act: -0.0000

Data Index: 506543 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.5045. Min Act: -0.0000

Data Index: 783690 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.4261. Min Act: -0.0000

Data Index: 745067 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.4105. Min Act: -0.0000

Data Index: 885090 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.3662. Min Act: -0.0000

Data Index: 214765 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.5527. Min Act: -0.0000

Data Index: 82623 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 6.0131. Min Range: -6.0131

Max Act: 4.1988. Min Act: -0.0000

Data Index: 307128 (C4 (Web Text))

Max Activating Token Index: 338