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

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

Neuron 419 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.8088. Min Act: -0.0001

Data Index: 41383 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.6928. Min Act: -0.0001

Data Index: 355033 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1217648 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.6668. Min Act: -0.0001

Data Index: 440240 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5980. Min Act: -0.0001

Data Index: 411375 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5790. Min Act: -0.0001

Data Index: 410864 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5942. Min Act: -0.0001

Data Index: 589714 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5251. Min Act: -0.0000

Data Index: 61492 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5149. Min Act: -0.0001

Data Index: 1193157 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4913. Min Act: -0.0001

Data Index: 19417 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.5711. Min Act: -0.0001

Data Index: 567778 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4937. Min Act: -0.0001

Data Index: 716497 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4672. Min Act: -0.0001

Data Index: 469627 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4431. Min Act: -0.0000

Data Index: 482129 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4832. Min Act: -0.0001

Data Index: 561696 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4502. Min Act: -0.0001

Data Index: 1074941 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4453. Min Act: -0.0001

Data Index: 558015 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.3813. Min Act: -0.0000

Data Index: 52467 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.4323. Min Act: -0.0000

Data Index: 282611 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.8088. Min Range: -0.8088

Max Act: 0.3892. Min Act: -0.0000

Data Index: 157891 (C4 (Web Text))

Max Activating Token Index: 254