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

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

Neuron 3002 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1129701 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8729. Min Act: -0.0001

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.9206. Min Act: -0.0001

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8337. Min Act: -0.0001

Data Index: 970299 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.7653. Min Act: -0.0001

Data Index: 1308863 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.7521. Min Act: -0.0002

Data Index: 535485 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8748. Min Act: -0.0001

Data Index: 1224703 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8092. Min Act: -0.0001

Data Index: 832407 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.7766. Min Act: -0.0001

Data Index: 618621 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.7892. Min Act: -0.0001

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8380. Min Act: -0.0002

Data Index: 1032363 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8410. Min Act: -0.0001

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8598. Min Act: -0.0001

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.6983. Min Act: -0.0001

Data Index: 693607 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8385. Min Act: -0.0002

Data Index: 495781 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.8099. Min Act: -0.0001

Data Index: 816522 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.7054. Min Act: -0.0002

Data Index: 1234992 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.7138. Min Act: -0.0002

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.7823. Min Act: -0.0002

Data Index: 226808 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.9206. Min Range: -0.9206

Max Act: 0.6851. Min Act: -0.0001

Data Index: 513397 (C4 (Web Text))

Max Activating Token Index: 337