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

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

Neuron 3730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.4322. Min Act: -0.0000

Data Index: 997213 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.4366. Min Act: -0.0000

Data Index: 839766 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1161717 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3983. Min Act: -0.0000

Data Index: 29296 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1081965 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3243. Min Act: -0.0000

Data Index: 272315 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1303057 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1118218 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3112. Min Act: -0.0000

Data Index: 9076 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3110. Min Act: -0.0000

Data Index: 802286 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2943. Min Act: -0.0000

Data Index: 516783 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3151. Min Act: -0.0000

Data Index: 830548 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2998. Min Act: -0.0000

Data Index: 819634 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2979. Min Act: -0.0000

Data Index: 630456 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2875. Min Act: -0.0000

Data Index: 836872 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2956. Min Act: -0.0000

Data Index: 184588 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1221072 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2935. Min Act: -0.0000

Data Index: 104186 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2907. Min Act: -0.0000

Data Index: 948825 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1307023 (C4 (Web Text))

Max Activating Token Index: 811