Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5466 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2626. Min Range: -2.2626

Max Act: 2.2545. Min Act: -0.0000

Data Index: 335686 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 2.2626. Min Range: -2.2626

Max Act: 2.2626. Min Act: -0.0001

Data Index: 693907 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 2.2626. Min Range: -2.2626

Max Act: 2.1553. Min Act: -0.0001

Data Index: 723918 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1078858 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1278807 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.3091. Min Act: -0.0001

Data Index: 264139 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.2515. Min Act: -0.0001

Data Index: 490404 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1158001 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.2514. Min Act: -0.0000

Data Index: 938535 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1189889 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.0724. Min Act: -0.0000

Data Index: 419840 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1201. Min Act: -0.0000

Data Index: 3290 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1366. Min Act: -0.0000

Data Index: 622264 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1313. Min Act: -0.0000

Data Index: 742940 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1236. Min Act: -0.0000

Data Index: 594457 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1692. Min Act: -0.0000

Data Index: 363111 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.0303. Min Act: -0.0000

Data Index: 573383 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.0781. Min Act: -0.0001

Data Index: 860419 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1171039 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 2.2626. Min Range: -2.2626

Max Act: 1.0749. Min Act: -0.0001

Data Index: 461036 (C4 (Web Text))

Max Activating Token Index: 491