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

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

Neuron 2153 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: 3.3315. Min Range: -3.3315

Max Act: 3.3315. Min Act: -0.0000

Data Index: 864775 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.3315. Min Range: -3.3315

Max Act: 3.0092. Min Act: -0.0000

Data Index: 330264 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.3315. Min Range: -3.3315

Max Act: 3.1939. Min Act: -0.0000

Data Index: 1365116 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 3.3315. Min Range: -3.3315

Max Act: 3.0376. Min Act: -0.0000

Data Index: 1280200 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.9940. Min Act: -0.0000

Data Index: 290797 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.9104. Min Act: -0.0000

Data Index: 491160 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 3.3315. Min Range: -3.3315

Max Act: 3.0485. Min Act: -0.0000

Data Index: 467466 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 3.3315. Min Range: -3.3315

Max Act: 3.0154. Min Act: -0.0000

Data Index: 1399848 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.7001. Min Act: -0.0000

Data Index: 947196 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.7008. Min Act: -0.0000

Data Index: 276630 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.6304. Min Act: -0.0000

Data Index: 1382989 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.7251. Min Act: -0.0000

Data Index: 1458988 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.7038. Min Act: -0.0000

Data Index: 1494288 (Python Code)

Max Activating Token Index: 327

Text #13

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.6758. Min Act: -0.0000

Data Index: 1426101 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.5292. Min Act: -0.0000

Data Index: 784782 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.7942. Min Act: -0.0000

Data Index: 242226 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.6326. Min Act: -0.0000

Data Index: 762268 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.6320. Min Act: -0.0000

Data Index: 1190539 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.6383. Min Act: -0.0000

Data Index: 1565518 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 3.3315. Min Range: -3.3315

Max Act: 2.4992. Min Act: -0.0000

Data Index: 1367379 (Python Code)

Max Activating Token Index: 299