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

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

Neuron 435 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4038. Min Range: -2.4038

Max Act: 2.4038. Min Act: -0.0000

Data Index: 1233569 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.9221. Min Act: -0.0000

Data Index: 738019 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.8279. Min Act: -0.0000

Data Index: 348330 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.8324. Min Act: -0.0000

Data Index: 836063 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.7362. Min Act: -0.0000

Data Index: 774702 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.7110. Min Act: -0.0000

Data Index: 587539 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.7177. Min Act: -0.0000

Data Index: 1321819 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.6875. Min Act: -0.0000

Data Index: 440523 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5943. Min Act: -0.0000

Data Index: 94776 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.6723. Min Act: -0.0000

Data Index: 865907 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5848. Min Act: -0.0000

Data Index: 127442 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5811. Min Act: -0.0000

Data Index: 144054 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5693. Min Act: -0.0000

Data Index: 845536 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1066157 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.6103. Min Act: -0.0000

Data Index: 638888 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5981. Min Act: -0.0000

Data Index: 654804 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5957. Min Act: -0.0000

Data Index: 1027419 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5581. Min Act: -0.0000

Data Index: 765873 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.6035. Min Act: -0.0000

Data Index: 404796 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.4038. Min Range: -2.4038

Max Act: 1.5471. Min Act: -0.0000

Data Index: 864961 (C4 (Web Text))

Max Activating Token Index: 917