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

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

Neuron 4328 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3753. Min Act: -0.0000

Data Index: 738283 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.3104. Min Act: -0.0000

Data Index: 671759 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2838. Min Act: -0.0000

Data Index: 906582 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2830. Min Act: -0.0000

Data Index: 224279 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1026678 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2507. Min Act: -0.0000

Data Index: 363227 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2557. Min Act: -0.0000

Data Index: 622055 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2504. Min Act: -0.0000

Data Index: 164783 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2505. Min Act: -0.0000

Data Index: 91929 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2485. Min Act: -0.0000

Data Index: 957844 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2552. Min Act: -0.0000

Data Index: 670961 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2476. Min Act: -0.0000

Data Index: 970239 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2623. Min Act: -0.0000

Data Index: 126380 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2471. Min Act: -0.0000

Data Index: 971596 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2533. Min Act: -0.0000

Data Index: 179380 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2449. Min Act: -0.0000

Data Index: 261240 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1229740 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1281921 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1180101 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.3753. Min Range: -0.3753

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1002492 (C4 (Web Text))

Max Activating Token Index: 522