Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4778. Min Act: -0.0001

Data Index: 991697 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.4099. Min Act: -0.0001

Data Index: 462632 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3791. Min Act: -0.0000

Data Index: 525079 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1102704 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2940. Min Act: -0.0001

Data Index: 989293 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.3011. Min Act: -0.0001

Data Index: 28952 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2866. Min Act: -0.0000

Data Index: 537671 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2710. Min Act: -0.0000

Data Index: 194111 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2870. Min Act: -0.0000

Data Index: 417558 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2790. Min Act: -0.0001

Data Index: 1127121 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2724. Min Act: -0.0000

Data Index: 101888 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2719. Min Act: -0.0000

Data Index: 115647 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2762. Min Act: -0.0001

Data Index: 516104 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2639. Min Act: -0.0001

Data Index: 311301 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2638. Min Act: -0.0001

Data Index: 377149 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2621. Min Act: -0.0001

Data Index: 966540 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2423. Min Act: -0.0001

Data Index: 1181444 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1353548 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2578. Min Act: -0.0001

Data Index: 761396 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.4778. Min Range: -0.4778

Max Act: 0.2481. Min Act: -0.0000

Data Index: 288008 (C4 (Web Text))

Max Activating Token Index: 343