Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3323 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.6380. Min Act: -0.0000

Data Index: 303087 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.5395. Min Act: -0.0000

Data Index: 426026 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.5972. Min Act: -0.0000

Data Index: 460123 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1167374 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.5722. Min Act: -0.0000

Data Index: 96840 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.5390. Min Act: -0.0000

Data Index: 742010 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.5142. Min Act: -0.0000

Data Index: 15830 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.5130. Min Act: -0.0000

Data Index: 631092 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4993. Min Act: -0.0000

Data Index: 95953 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1231117 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4695. Min Act: -0.0000

Data Index: 51331 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4586. Min Act: -0.0000

Data Index: 893563 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1177123 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4381. Min Act: -0.0000

Data Index: 527211 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4224. Min Act: -0.0000

Data Index: 954947 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1287304 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1258722 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4130. Min Act: -0.0000

Data Index: 871204 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.4091. Min Act: -0.0000

Data Index: 592059 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.6380. Min Range: -0.6380

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1120607 (C4 (Web Text))

Max Activating Token Index: 174