Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3084 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.6363. Min Act: -0.0001

Data Index: 168069 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5628. Min Act: -0.0001

Data Index: 514064 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1181896 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5637. Min Act: -0.0001

Data Index: 604660 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5901. Min Act: -0.0001

Data Index: 953031 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5603. Min Act: -0.0001

Data Index: 663017 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5415. Min Act: -0.0001

Data Index: 400178 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5106. Min Act: -0.0001

Data Index: 1105193 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5262. Min Act: -0.0001

Data Index: 1333042 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5312. Min Act: -0.0001

Data Index: 1145896 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5338. Min Act: -0.0001

Data Index: 1046831 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5207. Min Act: -0.0001

Data Index: 545258 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5246. Min Act: -0.0001

Data Index: 101570 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4972. Min Act: -0.0001

Data Index: 764350 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4883. Min Act: -0.0001

Data Index: 502774 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5054. Min Act: -0.0001

Data Index: 172396 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4638. Min Act: -0.0001

Data Index: 771877 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4797. Min Act: -0.0001

Data Index: 158915 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.4924. Min Act: -0.0001

Data Index: 232920 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.6363. Min Range: -0.6363

Max Act: 0.5022. Min Act: -0.0001

Data Index: 1180850 (C4 (Web Text))

Max Activating Token Index: 987