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

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

Neuron 1124 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2496. Min Range: -2.2496

Max Act: 2.2496. Min Act: -0.0000

Data Index: 1325070 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1262978 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1226246 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.6884. Min Act: -0.0000

Data Index: 840491 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.7023. Min Act: -0.0000

Data Index: 1103420 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.5939. Min Act: -0.0000

Data Index: 95526 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.4616. Min Act: -0.0000

Data Index: 32584 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.4050. Min Act: -0.0000

Data Index: 1027074 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1030834 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.6224. Min Act: -0.0000

Data Index: 719042 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.4619. Min Act: -0.0000

Data Index: 303359 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.2774. Min Act: -0.0000

Data Index: 860819 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.3484. Min Act: -0.0000

Data Index: 947266 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.3485. Min Act: -0.0000

Data Index: 756798 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.3097. Min Act: -0.0000

Data Index: 950258 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1036165 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.2967. Min Act: -0.0000

Data Index: 574399 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.2536. Min Act: -0.0000

Data Index: 633355 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.3173. Min Act: -0.0000

Data Index: 164169 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 2.2496. Min Range: -2.2496

Max Act: 1.2607. Min Act: -0.0000

Data Index: 205928 (C4 (Web Text))

Max Activating Token Index: 966