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

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

Neuron 597 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: 0.9695. Min Range: -0.9695

Max Act: 0.9695. Min Act: -0.0001

Data Index: 813252 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7825. Min Act: -0.0002

Data Index: 1270099 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8568. Min Act: -0.0002

Data Index: 645115 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7754. Min Act: -0.0002

Data Index: 850271 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7792. Min Act: -0.0001

Data Index: 681914 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7964. Min Act: -0.0002

Data Index: 1084346 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8093. Min Act: -0.0001

Data Index: 1026814 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7588. Min Act: -0.0002

Data Index: 861141 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7831. Min Act: -0.0002

Data Index: 244612 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1183034 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.6974. Min Act: -0.0001

Data Index: 119709 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7177. Min Act: -0.0002

Data Index: 1292367 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7637. Min Act: -0.0002

Data Index: 423479 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7107. Min Act: -0.0001

Data Index: 134468 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7334. Min Act: -0.0002

Data Index: 1061192 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7720. Min Act: -0.0001

Data Index: 483437 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7450. Min Act: -0.0002

Data Index: 494888 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.8168. Min Act: -0.0001

Data Index: 869169 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.7442. Min Act: -0.0001

Data Index: 997249 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.9695. Min Range: -0.9695

Max Act: 0.6383. Min Act: -0.0001

Data Index: 520049 (C4 (Web Text))

Max Activating Token Index: 714