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

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

Neuron 1178 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1197. Min Range: -1.1197

Max Act: 1.1197. Min Act: -0.0000

Data Index: 977723 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.9989. Min Act: -0.0001

Data Index: 1325418 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.8025. Min Act: -0.0000

Data Index: 530671 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1284260 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7771. Min Act: -0.0001

Data Index: 911369 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7709. Min Act: -0.0001

Data Index: 678178 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7435. Min Act: -0.0001

Data Index: 176986 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7699. Min Act: -0.0000

Data Index: 980436 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7330. Min Act: -0.0000

Data Index: 43744 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7249. Min Act: -0.0000

Data Index: 751331 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7289. Min Act: -0.0001

Data Index: 928672 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1327020 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.6770. Min Act: -0.0000

Data Index: 677566 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.6622. Min Act: -0.0001

Data Index: 705835 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.6962. Min Act: -0.0000

Data Index: 879300 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1189397 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.7076. Min Act: -0.0000

Data Index: 787830 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.6568. Min Act: -0.0001

Data Index: 671243 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.6988. Min Act: -0.0001

Data Index: 202070 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.1197. Min Range: -1.1197

Max Act: 0.6942. Min Act: -0.0000

Data Index: 468628 (C4 (Web Text))

Max Activating Token Index: 180