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

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

Neuron 1507 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.9191. Min Act: -0.0001

Data Index: 452783 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.9091. Min Act: -0.0001

Data Index: 15283 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.8444. Min Act: -0.0001

Data Index: 762211 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.8174. Min Act: -0.0001

Data Index: 368819 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.8442. Min Act: -0.0001

Data Index: 139789 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.8363. Min Act: -0.0001

Data Index: 68937 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7959. Min Act: -0.0001

Data Index: 1167857 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.8379. Min Act: -0.0001

Data Index: 232415 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7561. Min Act: -0.0001

Data Index: 467074 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7970. Min Act: -0.0001

Data Index: 62094 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7698. Min Act: -0.0001

Data Index: 325100 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7718. Min Act: -0.0001

Data Index: 475777 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.8191. Min Act: -0.0001

Data Index: 58732 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.8186. Min Act: -0.0001

Data Index: 1136379 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7925. Min Act: -0.0001

Data Index: 1024067 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7907. Min Act: -0.0001

Data Index: 1324054 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7627. Min Act: -0.0001

Data Index: 640061 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1336727 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7713. Min Act: -0.0001

Data Index: 763389 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.9191. Min Range: -0.9191

Max Act: 0.7654. Min Act: -0.0001

Data Index: 1199606 (C4 (Web Text))

Max Activating Token Index: 183