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

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

Neuron 4022 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.8113. Min Act: -0.0001

Data Index: 747696 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.6161. Min Act: -0.0001

Data Index: 41947 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.5708. Min Act: -0.0001

Data Index: 1037160 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.5555. Min Act: -0.0001

Data Index: 28739 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.4882. Min Act: -0.0001

Data Index: 946584 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.5007. Min Act: -0.0001

Data Index: 1337732 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.4520. Min Act: -0.0001

Data Index: 848668 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.3960. Min Act: -0.0001

Data Index: 1102968 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.3456. Min Act: -0.0001

Data Index: 189030 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.5108. Min Act: -0.0001

Data Index: 1007456 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.2645. Min Act: -0.0001

Data Index: 263793 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.3296. Min Act: -0.0001

Data Index: 1243408 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.3167. Min Act: -0.0001

Data Index: 897934 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.2785. Min Act: -0.0001

Data Index: 470217 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.2796. Min Act: -0.0001

Data Index: 876595 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.1527. Min Act: -0.0001

Data Index: 1120110 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.1900. Min Act: -0.0001

Data Index: 1229143 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.2343. Min Act: -0.0001

Data Index: 523445 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.1951. Min Act: -0.0001

Data Index: 1129129 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 1.8113. Min Range: -1.8113

Max Act: 1.1923. Min Act: -0.0001

Data Index: 1310521 (C4 (Web Text))

Max Activating Token Index: 860