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

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

Neuron 2065 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6747. Min Act: -0.0001

Data Index: 466463 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6660. Min Act: -0.0001

Data Index: 887773 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6553. Min Act: -0.0001

Data Index: 698186 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5705. Min Act: -0.0001

Data Index: 749940 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6080. Min Act: -0.0001

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5969. Min Act: -0.0001

Data Index: 277618 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5301. Min Act: -0.0000

Data Index: 447231 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5718. Min Act: -0.0001

Data Index: 344290 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5049. Min Act: -0.0001

Data Index: 655828 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5502. Min Act: -0.0001

Data Index: 810967 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1227322 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5977. Min Act: -0.0001

Data Index: 1638669 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1355566 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1335195 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.4714. Min Act: -0.0001

Data Index: 986852 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.4986. Min Act: -0.0001

Data Index: 886728 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5105. Min Act: -0.0000

Data Index: 953140 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5128. Min Act: -0.0001

Data Index: 66464 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1145312 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.4999. Min Act: -0.0001

Data Index: 591028 (C4 (Web Text))

Max Activating Token Index: 557