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

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

Neuron 4672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5988. Min Act: -0.0000

Data Index: 83243 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4208. Min Act: -0.0000

Data Index: 63719 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4108. Min Act: -0.0000

Data Index: 132773 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.8083. Min Act: -0.0000

Data Index: 1267661 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.7703. Min Act: -0.0000

Data Index: 1309827 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4590. Min Act: -0.0000

Data Index: 576595 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5855. Min Act: -0.0000

Data Index: 108549 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4012. Min Act: -0.0000

Data Index: 873767 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5502. Min Act: -0.0000

Data Index: 1243525 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4090. Min Act: -0.0000

Data Index: 1002107 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.2643. Min Act: -0.0000

Data Index: 336076 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.2594. Min Act: -0.0000

Data Index: 98660 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.1478. Min Act: -0.0000

Data Index: 998497 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3176. Min Act: -0.0000

Data Index: 35253 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4578. Min Act: -0.0000

Data Index: 790173 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.1282. Min Act: -0.0000

Data Index: 141333 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.2708. Min Act: -0.0000

Data Index: 788339 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.0920. Min Act: -0.0001

Data Index: 1047467 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3263. Min Act: -0.0000

Data Index: 761981 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.3013. Min Act: -0.0000

Data Index: 1171936 (C4 (Web Text))

Max Activating Token Index: 513