Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1508 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1046581 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1520478 (Python Code)

Max Activating Token Index: 127

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0398. Min Act: -0.0003

Data Index: 571046 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0368. Min Act: -0.0003

Data Index: 390056 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1402043 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0388. Min Act: -0.0003

Data Index: 3457 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1046163 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1250847 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0346. Min Act: -0.0003

Data Index: 324654 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0318. Min Act: -0.0003

Data Index: 517733 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1024365 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0327. Min Act: -0.0003

Data Index: 529392 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0331. Min Act: -0.0003

Data Index: 411082 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0318. Min Act: -0.0003

Data Index: 999946 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0305. Min Act: -0.0003

Data Index: 931862 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1478811 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1088906 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0311. Min Act: -0.0003

Data Index: 644261 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1123143 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0303. Min Act: -0.0003

Data Index: 166200 (C4 (Web Text))

Max Activating Token Index: 283