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

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

Neuron 55 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: 5.2970. Min Range: -5.2970

Max Act: 5.2970. Min Act: -0.0000

Data Index: 863230 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 5.2970. Min Range: -5.2970

Max Act: 5.0290. Min Act: -0.0000

Data Index: 605419 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 5.2970. Min Range: -5.2970

Max Act: 4.3766. Min Act: -0.0000

Data Index: 633822 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 5.2970. Min Range: -5.2970

Max Act: 4.3554. Min Act: -0.0000

Data Index: 375629 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 5.2970. Min Range: -5.2970

Max Act: 4.1458. Min Act: -0.0000

Data Index: 622973 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 5.2970. Min Range: -5.2970

Max Act: 4.1153. Min Act: -0.0000

Data Index: 750400 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.8855. Min Act: -0.0000

Data Index: 466585 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.4702. Min Act: -0.0000

Data Index: 498739 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.2461. Min Act: -0.0000

Data Index: 973796 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.3395. Min Act: -0.0000

Data Index: 742243 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 5.2970. Min Range: -5.2970

Max Act: 2.9381. Min Act: -0.0000

Data Index: 1257873 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.0729. Min Act: -0.0000

Data Index: 26936 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.0140. Min Act: -0.0000

Data Index: 812811 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.0907. Min Act: -0.0000

Data Index: 58383 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.0257. Min Act: -0.0000

Data Index: 924651 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 5.2970. Min Range: -5.2970

Max Act: 3.0049. Min Act: -0.0000

Data Index: 841297 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 5.2970. Min Range: -5.2970

Max Act: 2.7056. Min Act: -0.0000

Data Index: 26387 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 5.2970. Min Range: -5.2970

Max Act: 2.9579. Min Act: -0.0000

Data Index: 343000 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 5.2970. Min Range: -5.2970

Max Act: 2.9133. Min Act: -0.0000

Data Index: 1343439 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 5.2970. Min Range: -5.2970

Max Act: 2.7435. Min Act: -0.0000

Data Index: 170777 (C4 (Web Text))

Max Activating Token Index: 36