Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3279 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.3472. Min Act: 0.0000

Data Index: 476165 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.3286. Min Act: -0.0000

Data Index: 690878 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.3046. Min Act: -0.0000

Data Index: 728928 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2847. Min Act: -0.0000

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2914. Min Act: -0.0000

Data Index: 474189 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2807. Min Act: -0.0000

Data Index: 76826 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2965. Min Act: -0.0000

Data Index: 135128 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1163951 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2731. Min Act: -0.0000

Data Index: 584497 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2729. Min Act: 0.0000

Data Index: 1073421 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1303395 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2921. Min Act: -0.0000

Data Index: 804735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1157112 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2728. Min Act: 0.0000

Data Index: 611778 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2695. Min Act: 0.0002

Data Index: 757710 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2731. Min Act: -0.0000

Data Index: 989040 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2582. Min Act: -0.0000

Data Index: 614404 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2675. Min Act: -0.0000

Data Index: 556114 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1028554 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.3472. Min Range: -0.3472

Max Act: 0.2638. Min Act: -0.0000

Data Index: 380780 (C4 (Web Text))

Max Activating Token Index: 774