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

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

Neuron 304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6114. Min Range: -2.6114

Max Act: 2.6114. Min Act: -0.0000

Data Index: 14596 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 2.6114. Min Range: -2.6114

Max Act: 2.1147. Min Act: -0.0000

Data Index: 156225 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 2.6114. Min Range: -2.6114

Max Act: 1.7587. Min Act: -0.0000

Data Index: 1065112 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 2.6114. Min Range: -2.6114

Max Act: 1.9151. Min Act: -0.0000

Data Index: 725673 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 2.6114. Min Range: -2.6114

Max Act: 1.4274. Min Act: -0.0000

Data Index: 763457 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 2.6114. Min Range: -2.6114

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1337896 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 2.6114. Min Range: -2.6114

Max Act: 1.1715. Min Act: -0.0000

Data Index: 410820 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 2.6114. Min Range: -2.6114

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1022855 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.7560. Min Act: -0.0000

Data Index: 232782 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.8335. Min Act: -0.0000

Data Index: 4852 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.7345. Min Act: -0.0000

Data Index: 131406 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1321952 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.5870. Min Act: -0.0000

Data Index: 813777 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.7091. Min Act: -0.0000

Data Index: 774809 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.8134. Min Act: -0.0000

Data Index: 953656 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.8302. Min Act: -0.0000

Data Index: 32965 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1034643 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.8655. Min Act: -0.0000

Data Index: 752875 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.8307. Min Act: -0.0000

Data Index: 656517 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.6114. Min Range: -2.6114

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1341423 (C4 (Web Text))

Max Activating Token Index: 905