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

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

Neuron 3592 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.9049. Min Act: -0.0001

Data Index: 1247141 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.6979. Min Act: -0.0000

Data Index: 295973 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.5242. Min Act: -0.0001

Data Index: 896068 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.5405. Min Act: -0.0001

Data Index: 611626 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1274091 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.3376. Min Act: -0.0001

Data Index: 257163 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2520. Min Act: -0.0001

Data Index: 1086272 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.1990. Min Act: -0.0000

Data Index: 419747 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2665. Min Act: -0.0000

Data Index: 584899 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.3054. Min Act: -0.0001

Data Index: 660571 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2619. Min Act: -0.0000

Data Index: 259449 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.3461. Min Act: -0.0001

Data Index: 325542 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1354690 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2529. Min Act: -0.0001

Data Index: 905289 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2849. Min Act: -0.0001

Data Index: 1075795 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2910. Min Act: -0.0000

Data Index: 686390 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2829. Min Act: -0.0001

Data Index: 731723 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2670. Min Act: -0.0001

Data Index: 654748 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2282. Min Act: -0.0001

Data Index: 406411 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.2582. Min Act: -0.0000

Data Index: 919388 (C4 (Web Text))

Max Activating Token Index: 850