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

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

Neuron 2538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0502. Min Range: -1.0502

Max Act: 1.0502. Min Act: -0.0001

Data Index: 1590873 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9505. Min Act: -0.0001

Data Index: 1477435 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8806. Min Act: -0.0001

Data Index: 1570069 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8870. Min Act: -0.0001

Data Index: 1436102 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9239. Min Act: -0.0001

Data Index: 1495364 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8715. Min Act: -0.0001

Data Index: 1418290 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8423. Min Act: -0.0001

Data Index: 1443147 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7706. Min Act: -0.0001

Data Index: 1385897 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7915. Min Act: -0.0001

Data Index: 1492052 (Python Code)

Max Activating Token Index: 488

Text #9

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9177. Min Act: -0.0001

Data Index: 1441179 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8125. Min Act: -0.0001

Data Index: 1586046 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8612. Min Act: -0.0001

Data Index: 1408056 (Python Code)

Max Activating Token Index: 374

Text #12

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8371. Min Act: -0.0001

Data Index: 1647312 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7639. Min Act: -0.0001

Data Index: 1365306 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8596. Min Act: -0.0001

Data Index: 1509720 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8596. Min Act: -0.0001

Data Index: 1629572 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8543. Min Act: -0.0001

Data Index: 1634061 (Python Code)

Max Activating Token Index: 570

Text #17

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8507. Min Act: -0.0001

Data Index: 1432392 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8009. Min Act: -0.0001

Data Index: 1639020 (Python Code)

Max Activating Token Index: 502

Text #19

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8164. Min Act: -0.0001

Data Index: 1549147 (Python Code)

Max Activating Token Index: 183