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

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

Neuron 2282 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3321. Min Act: -0.0002

Data Index: 1499004 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3019. Min Act: -0.0002

Data Index: 849047 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2979. Min Act: -0.0002

Data Index: 1585314 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3009. Min Act: -0.0002

Data Index: 1419789 (Python Code)

Max Activating Token Index: 512

Text #4

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2924. Min Act: -0.0002

Data Index: 1506084 (Python Code)

Max Activating Token Index: 714

Text #5

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2885. Min Act: -0.0002

Data Index: 1602612 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2906. Min Act: -0.0002

Data Index: 1620094 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2907. Min Act: -0.0002

Data Index: 1385286 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2891. Min Act: -0.0002

Data Index: 1432887 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2856. Min Act: -0.0002

Data Index: 1453715 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2817. Min Act: -0.0002

Data Index: 1402813 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2833. Min Act: -0.0002

Data Index: 98465 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2805. Min Act: -0.0002

Data Index: 1646068 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2845. Min Act: -0.0002

Data Index: 1402801 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2829. Min Act: -0.0002

Data Index: 1625841 (Python Code)

Max Activating Token Index: 925

Text #15

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2739. Min Act: -0.0002

Data Index: 428928 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2761. Min Act: -0.0002

Data Index: 1361197 (Python Code)

Max Activating Token Index: 112

Text #17

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2774. Min Act: -0.0002

Data Index: 1474126 (Python Code)

Max Activating Token Index: 213

Text #18

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2802. Min Act: -0.0002

Data Index: 1622781 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2718. Min Act: -0.0002

Data Index: 1424638 (Python Code)

Max Activating Token Index: 67