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

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

Neuron 2793 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: 1.3984. Min Range: -1.3984

Max Act: 1.3984. Min Act: -0.0002

Data Index: 766068 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.8948. Min Act: -0.0002

Data Index: 964831 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.8827. Min Act: -0.0001

Data Index: 36694 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.8323. Min Act: -0.0002

Data Index: 112023 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.8311. Min Act: -0.0001

Data Index: 1216174 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.8711. Min Act: -0.0001

Data Index: 1278659 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.8179. Min Act: -0.0001

Data Index: 892305 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7887. Min Act: -0.0001

Data Index: 1308019 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7998. Min Act: -0.0002

Data Index: 890858 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7484. Min Act: -0.0001

Data Index: 125431 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7728. Min Act: -0.0001

Data Index: 272774 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7368. Min Act: -0.0002

Data Index: 774879 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7335. Min Act: -0.0002

Data Index: 974292 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7309. Min Act: -0.0001

Data Index: 910186 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7012. Min Act: -0.0001

Data Index: 279332 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7938. Min Act: -0.0002

Data Index: 448092 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7336. Min Act: -0.0002

Data Index: 710634 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7042. Min Act: -0.0001

Data Index: 990484 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.7319. Min Act: -0.0001

Data Index: 731624 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.6797. Min Act: -0.0001

Data Index: 882248 (C4 (Web Text))

Max Activating Token Index: 1009