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

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

Neuron 4038 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3078. Min Range: -9.3078

Max Act: 9.3078. Min Act: -0.0001

Data Index: 842006 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 9.3078. Min Range: -9.3078

Max Act: 7.0241. Min Act: -0.0000

Data Index: 505722 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 9.3078. Min Range: -9.3078

Max Act: 7.9131. Min Act: -0.0000

Data Index: 334428 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.4451. Min Act: -0.0000

Data Index: 122377 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.3209. Min Act: -0.0000

Data Index: 205883 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.9852. Min Act: -0.0000

Data Index: 930920 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.5316. Min Act: -0.0000

Data Index: 674550 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.3404. Min Act: -0.0000

Data Index: 516017 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.4308. Min Act: -0.0000

Data Index: 557898 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.0330. Min Act: -0.0000

Data Index: 257728 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 9.3078. Min Range: -9.3078

Max Act: 5.6743. Min Act: -0.0000

Data Index: 157024 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.1259. Min Act: -0.0000

Data Index: 1127647 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 9.3078. Min Range: -9.3078

Max Act: 5.7612. Min Act: -0.0000

Data Index: 57676 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.3753. Min Act: -0.0000

Data Index: 717352 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.0116. Min Act: -0.0000

Data Index: 947296 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 9.3078. Min Range: -9.3078

Max Act: 6.3456. Min Act: -0.0000

Data Index: 504780 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 9.3078. Min Range: -9.3078

Max Act: 5.8878. Min Act: -0.0000

Data Index: 1237615 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 9.3078. Min Range: -9.3078

Max Act: 5.6630. Min Act: -0.0000

Data Index: 1256557 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 9.3078. Min Range: -9.3078

Max Act: 5.2803. Min Act: -0.0000

Data Index: 763293 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 9.3078. Min Range: -9.3078

Max Act: 5.5435. Min Act: -0.0000

Data Index: 71692 (C4 (Web Text))

Max Activating Token Index: 421