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

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

Neuron 2049 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: 0.3534. Min Range: -0.3534

Max Act: 0.3502. Min Act: -0.0001

Data Index: 1002442 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.3534. Min Act: -0.0001

Data Index: 660695 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2935. Min Act: -0.0001

Data Index: 456347 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1244097 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2696. Min Act: -0.0000

Data Index: 68724 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2843. Min Act: -0.0001

Data Index: 27587 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2939. Min Act: -0.0000

Data Index: 970949 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2791. Min Act: -0.0000

Data Index: 210335 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2926. Min Act: -0.0000

Data Index: 453247 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2877. Min Act: -0.0001

Data Index: 801695 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1291541 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2204. Min Act: -0.0000

Data Index: 968894 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2721. Min Act: -0.0001

Data Index: 59065 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1217974 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2596. Min Act: -0.0000

Data Index: 66372 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2576. Min Act: -0.0001

Data Index: 999530 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2697. Min Act: -0.0000

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2575. Min Act: -0.0001

Data Index: 958092 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1229484 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2542. Min Act: -0.0000

Data Index: 596153 (C4 (Web Text))

Max Activating Token Index: 531