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

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

Neuron 3224 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: 0.4759. Min Range: -0.4759

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1354214 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4254. Min Act: -0.0000

Data Index: 647560 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1294121 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4018. Min Act: -0.0000

Data Index: 548018 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4483. Min Act: -0.0000

Data Index: 534462 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4265. Min Act: -0.0000

Data Index: 679789 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4228. Min Act: -0.0000

Data Index: 582261 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4466. Min Act: -0.0000

Data Index: 737288 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4271. Min Act: -0.0000

Data Index: 820909 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4032. Min Act: -0.0000

Data Index: 582176 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1228292 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4249. Min Act: -0.0000

Data Index: 995687 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4165. Min Act: -0.0000

Data Index: 762922 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4077. Min Act: -0.0000

Data Index: 555607 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1047175 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1288052 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3390. Min Act: -0.0000

Data Index: 293955 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3750. Min Act: -0.0000

Data Index: 180996 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3406. Min Act: -0.0000

Data Index: 524511 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1253144 (C4 (Web Text))

Max Activating Token Index: 980