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

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

Neuron 2436 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.9815. Min Act: -0.0000

Data Index: 1185740 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.7927. Min Act: -0.0000

Data Index: 567153 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.8399. Min Act: -0.0000

Data Index: 900740 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.8280. Min Act: -0.0000

Data Index: 1276878 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6529. Min Act: -0.0000

Data Index: 981601 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1168976 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6416. Min Act: -0.0000

Data Index: 1206073 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6166. Min Act: -0.0000

Data Index: 159042 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6017. Min Act: -0.0000

Data Index: 918657 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.3951. Min Act: -0.0000

Data Index: 543022 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.6442. Min Act: -0.0000

Data Index: 171267 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.5273. Min Act: -0.0000

Data Index: 991570 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.5910. Min Act: -0.0000

Data Index: 342840 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.4976. Min Act: -0.0000

Data Index: 983124 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.4918. Min Act: -0.0000

Data Index: 352356 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.5756. Min Act: -0.0000

Data Index: 82956 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.4555. Min Act: -0.0000

Data Index: 987965 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.4521. Min Act: -0.0000

Data Index: 438887 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.4482. Min Act: -0.0000

Data Index: 1259395 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 1.9815. Min Range: -1.9815

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1023443 (C4 (Web Text))

Max Activating Token Index: 385