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

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

Neuron 1639 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0379. Min Range: -1.0379

Max Act: 1.0379. Min Act: -0.0000

Data Index: 30963 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.6949. Min Act: -0.0000

Data Index: 262434 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.6410. Min Act: -0.0000

Data Index: 803896 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1098018 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5983. Min Act: 0.0000

Data Index: 328188 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5416. Min Act: -0.0000

Data Index: 441061 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5362. Min Act: -0.0000

Data Index: 449031 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5481. Min Act: -0.0000

Data Index: 798647 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5518. Min Act: -0.0000

Data Index: 475945 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5468. Min Act: -0.0000

Data Index: 470718 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5250. Min Act: 0.0000

Data Index: 1344757 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5418. Min Act: 0.0000

Data Index: 30649 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5188. Min Act: -0.0000

Data Index: 875861 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1236545 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.4896. Min Act: -0.0000

Data Index: 248655 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5320. Min Act: -0.0000

Data Index: 195068 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5105. Min Act: -0.0000

Data Index: 300195 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1151111 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.4832. Min Act: 0.0001

Data Index: 1052162 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 1.0379. Min Range: -1.0379

Max Act: 0.5063. Min Act: 0.0001

Data Index: 589403 (C4 (Web Text))

Max Activating Token Index: 682