Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3992. Min Range: -2.3992

Max Act: 2.3992. Min Act: -0.0000

Data Index: 93989 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 2.3992. Min Range: -2.3992

Max Act: 2.1388. Min Act: -0.0000

Data Index: 1290276 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 2.3992. Min Range: -2.3992

Max Act: 2.1873. Min Act: -0.0000

Data Index: 799055 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 2.3992. Min Range: -2.3992

Max Act: 2.1865. Min Act: -0.0000

Data Index: 272764 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.9138. Min Act: -0.0000

Data Index: 888155 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.3992. Min Range: -2.3992

Max Act: 2.0052. Min Act: -0.0000

Data Index: 1033026 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 2.3992. Min Range: -2.3992

Max Act: 2.0578. Min Act: -0.0000

Data Index: 219209 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.9057. Min Act: -0.0000

Data Index: 130973 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.5292. Min Act: -0.0000

Data Index: 368692 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.6618. Min Act: -0.0000

Data Index: 786084 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.7631. Min Act: -0.0000

Data Index: 1293499 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.7423. Min Act: -0.0000

Data Index: 608854 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.7312. Min Act: -0.0000

Data Index: 556008 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.7154. Min Act: -0.0000

Data Index: 515638 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.7145. Min Act: -0.0000

Data Index: 473682 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1343298 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.8997. Min Act: -0.0000

Data Index: 91730 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.8886. Min Act: -0.0000

Data Index: 1345854 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.5003. Min Act: -0.0000

Data Index: 1129796 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.3992. Min Range: -2.3992

Max Act: 1.7782. Min Act: -0.0000

Data Index: 76553 (C4 (Web Text))

Max Activating Token Index: 891