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

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

Neuron 2445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5457. Min Act: -0.0000

Data Index: 389214 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.2338. Min Act: -0.0001

Data Index: 241113 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.1691. Min Act: -0.0001

Data Index: 1099111 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.9930. Min Act: -0.0001

Data Index: 649150 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.0425. Min Act: -0.0001

Data Index: 45419 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.0345. Min Act: -0.0000

Data Index: 904161 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.0097. Min Act: -0.0001

Data Index: 216985 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.9761. Min Act: -0.0001

Data Index: 520580 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8546. Min Act: -0.0000

Data Index: 203440 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8207. Min Act: -0.0001

Data Index: 81623 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.0006. Min Act: -0.0001

Data Index: 678810 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8737. Min Act: -0.0000

Data Index: 587089 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.9564. Min Act: -0.0001

Data Index: 597043 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8605. Min Act: -0.0001

Data Index: 182843 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8335. Min Act: -0.0001

Data Index: 189026 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1156841 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.7982. Min Act: -0.0000

Data Index: 778886 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8195. Min Act: -0.0001

Data Index: 362160 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8533. Min Act: -0.0001

Data Index: 383438 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1274801 (C4 (Web Text))

Max Activating Token Index: 225