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

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

Neuron 169 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1228. Min Act: -0.0001

Data Index: 233560 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2831. Min Act: -0.0001

Data Index: 1280924 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2230. Min Act: -0.0001

Data Index: 13931 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0761. Min Act: -0.0001

Data Index: 558913 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9996. Min Act: -0.0001

Data Index: 344866 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0501. Min Act: -0.0001

Data Index: 966526 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0182. Min Act: -0.0001

Data Index: 55593 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0320. Min Act: -0.0001

Data Index: 333503 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0335. Min Act: -0.0001

Data Index: 533186 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0387. Min Act: -0.0001

Data Index: 81462 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9960. Min Act: -0.0001

Data Index: 920652 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9281. Min Act: -0.0001

Data Index: 501157 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9076. Min Act: -0.0001

Data Index: 267151 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9568. Min Act: -0.0001

Data Index: 200546 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0175. Min Act: -0.0001

Data Index: 1299683 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0080. Min Act: -0.0001

Data Index: 189935 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1029315 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.7987. Min Act: -0.0001

Data Index: 514680 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9057. Min Act: -0.0001

Data Index: 234306 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.7539. Min Act: -0.0001

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 705