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

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

Neuron 4008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.4884. Min Act: -0.0001

Data Index: 1537921 (Python Code)

Max Activating Token Index: 975

Text #1

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3881. Min Act: -0.0001

Data Index: 1512499 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3935. Min Act: -0.0001

Data Index: 1430178 (Python Code)

Max Activating Token Index: 277

Text #3

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3751. Min Act: -0.0001

Data Index: 1635001 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3753. Min Act: -0.0001

Data Index: 1397869 (Python Code)

Max Activating Token Index: 523

Text #5

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1285119 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2913. Min Act: -0.0001

Data Index: 1575824 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2955. Min Act: -0.0001

Data Index: 1448728 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.3353. Min Act: -0.0001

Data Index: 1604790 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2716. Min Act: -0.0001

Data Index: 1396641 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1462739 (Python Code)

Max Activating Token Index: 849

Text #11

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1115706 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2796. Min Act: -0.0001

Data Index: 13130 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2566. Min Act: -0.0000

Data Index: 645693 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1565298 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1593653 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2482. Min Act: -0.0001

Data Index: 1419316 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2464. Min Act: -0.0000

Data Index: 898569 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2575. Min Act: -0.0000

Data Index: 111201 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.4884. Min Range: -0.4884

Max Act: 0.2624. Min Act: -0.0001

Data Index: 246512 (C4 (Web Text))

Max Activating Token Index: 883