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

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

Neuron 2931 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.9946. Min Act: -0.0001

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.9119. Min Act: -0.0001

Data Index: 49244 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8539. Min Act: -0.0001

Data Index: 1009284 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8455. Min Act: -0.0001

Data Index: 1041652 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8947. Min Act: -0.0001

Data Index: 571920 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7838. Min Act: -0.0001

Data Index: 78509 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8070. Min Act: -0.0001

Data Index: 21761 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8490. Min Act: -0.0001

Data Index: 598892 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8192. Min Act: -0.0001

Data Index: 896355 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.9129. Min Act: -0.0001

Data Index: 1355116 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7910. Min Act: -0.0001

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.8457. Min Act: -0.0001

Data Index: 321406 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.6536. Min Act: -0.0001

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7356. Min Act: -0.0001

Data Index: 518734 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7505. Min Act: -0.0001

Data Index: 1015541 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7945. Min Act: -0.0001

Data Index: 901282 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7583. Min Act: -0.0001

Data Index: 842097 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7585. Min Act: -0.0001

Data Index: 901807 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7943. Min Act: -0.0001

Data Index: 788864 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.9946. Min Range: -0.9946

Max Act: 0.7269. Min Act: -0.0001

Data Index: 177394 (C4 (Web Text))

Max Activating Token Index: 39