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

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

Neuron 3017 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: 2.2523. Min Range: -2.2523

Max Act: 2.2523. Min Act: 0.0000

Data Index: 1080229 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.4969. Min Act: -0.0000

Data Index: 671556 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.5623. Min Act: -0.0000

Data Index: 50056 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.3874. Min Act: -0.0000

Data Index: 369107 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2946. Min Act: -0.0000

Data Index: 485157 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2446. Min Act: -0.0000

Data Index: 865393 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2105. Min Act: -0.0000

Data Index: 86923 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1596487 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1475721 (Python Code)

Max Activating Token Index: 959

Text #9

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2471. Min Act: -0.0000

Data Index: 669455 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1318881 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1164992 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1161550 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2003. Min Act: -0.0000

Data Index: 950814 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.1525. Min Act: 0.0000

Data Index: 697557 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.1883. Min Act: -0.0000

Data Index: 308561 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1638187 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1149710 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.1488. Min Act: -0.0000

Data Index: 775112 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 2.2523. Min Range: -2.2523

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1212306 (C4 (Web Text))

Max Activating Token Index: 727