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

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

Neuron 1071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1561096 (Python Code)

Max Activating Token Index: 297

Text #1

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8652. Min Act: -0.0000

Data Index: 449534 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1494638 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6721. Min Act: -0.0000

Data Index: 640196 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.8891. Min Act: -0.0000

Data Index: 568929 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1257398 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7671. Min Act: -0.0000

Data Index: 477787 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6982. Min Act: -0.0000

Data Index: 208866 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6212. Min Act: -0.0000

Data Index: 827987 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1245560 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7559. Min Act: -0.0000

Data Index: 924488 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1493450 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6616. Min Act: -0.0000

Data Index: 838390 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6653. Min Act: -0.0000

Data Index: 195238 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1074866 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1540275 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6347. Min Act: -0.0000

Data Index: 99201 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6538. Min Act: -0.0000

Data Index: 148143 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.6484. Min Act: -0.0000

Data Index: 582362 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.9423. Min Range: -0.9423

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1012422 (C4 (Web Text))

Max Activating Token Index: 408