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

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

Neuron 4100 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.9207. Min Act: -0.0000

Data Index: 519981 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.8082. Min Act: -0.0000

Data Index: 957264 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1023920 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7902. Min Act: -0.0000

Data Index: 799802 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.8012. Min Act: -0.0000

Data Index: 919766 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7759. Min Act: -0.0000

Data Index: 90716 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7415. Min Act: -0.0000

Data Index: 864584 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1007094 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7733. Min Act: -0.0000

Data Index: 7608 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7182. Min Act: -0.0000

Data Index: 899495 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1017205 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7092. Min Act: -0.0000

Data Index: 536860 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7520. Min Act: -0.0000

Data Index: 962177 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7341. Min Act: -0.0000

Data Index: 205208 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6604. Min Act: -0.0000

Data Index: 478433 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7218. Min Act: -0.0000

Data Index: 382853 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6970. Min Act: -0.0000

Data Index: 646586 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1393284 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6685. Min Act: -0.0000

Data Index: 672237 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.9207. Min Range: -0.9207

Max Act: 0.6875. Min Act: -0.0000

Data Index: 770068 (C4 (Web Text))

Max Activating Token Index: 886