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

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

Neuron 4067 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3363. Min Range: -7.3363

Max Act: 7.3363. Min Act: -0.0000

Data Index: 1225718 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 7.3363. Min Range: -7.3363

Max Act: 7.2791. Min Act: -0.0000

Data Index: 1351875 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.9277. Min Act: -0.0000

Data Index: 212587 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.9301. Min Act: -0.0000

Data Index: 1115107 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.9989. Min Act: -0.0000

Data Index: 539252 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 7.3363. Min Range: -7.3363

Max Act: 7.1883. Min Act: -0.0000

Data Index: 814513 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.7975. Min Act: -0.0000

Data Index: 34798 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.7179. Min Act: -0.0000

Data Index: 884667 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.6312. Min Act: -0.0000

Data Index: 952471 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.9809. Min Act: -0.0000

Data Index: 80500 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.8302. Min Act: -0.0000

Data Index: 689504 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.7670. Min Act: -0.0000

Data Index: 1240733 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.4269. Min Act: -0.0000

Data Index: 1097405 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.5262. Min Act: -0.0000

Data Index: 999578 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.7786. Min Act: -0.0000

Data Index: 277227 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 7.3363. Min Range: -7.3363

Max Act: 7.1486. Min Act: -0.0000

Data Index: 499993 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.9048. Min Act: -0.0000

Data Index: 1136548 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.3686. Min Act: -0.0000

Data Index: 41251 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.3702. Min Act: -0.0000

Data Index: 298093 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 7.3363. Min Range: -7.3363

Max Act: 6.8940. Min Act: -0.0000

Data Index: 990222 (C4 (Web Text))

Max Activating Token Index: 200