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

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

Neuron 1347 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0001

Data Index: 624683 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0992. Min Act: -0.0001

Data Index: 982791 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0965. Min Act: -0.0001

Data Index: 430214 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0919. Min Act: -0.0001

Data Index: 472826 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1459221 (Python Code)

Max Activating Token Index: 991

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1367392 (Python Code)

Max Activating Token Index: 1003

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0637. Min Act: -0.0001

Data Index: 895327 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0634. Min Act: -0.0001

Data Index: 526126 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1439627 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1374002 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0662. Min Act: -0.0001

Data Index: 975587 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1309324 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0624. Min Act: -0.0001

Data Index: 736603 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0665. Min Act: -0.0001

Data Index: 934166 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1077700 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1645004 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0510. Min Act: -0.0001

Data Index: 452252 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1585043 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1609042 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0540. Min Act: -0.0001

Data Index: 964845 (C4 (Web Text))

Max Activating Token Index: 652