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

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

Neuron 4420 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1677. Min Range: -2.1677

Max Act: 2.1677. Min Act: -0.0000

Data Index: 159120 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.8551. Min Act: -0.0000

Data Index: 16490 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.8705. Min Act: -0.0000

Data Index: 1346415 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.9334. Min Act: -0.0000

Data Index: 1304265 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.6372. Min Act: -0.0000

Data Index: 824948 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.7085. Min Act: -0.0000

Data Index: 334511 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.7193. Min Act: -0.0000

Data Index: 1342279 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.7957. Min Act: -0.0000

Data Index: 444786 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.5800. Min Act: -0.0000

Data Index: 873787 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.7597. Min Act: -0.0000

Data Index: 537759 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.6362. Min Act: -0.0000

Data Index: 595865 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.6981. Min Act: -0.0000

Data Index: 100324 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.6048. Min Act: -0.0000

Data Index: 378004 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.3969. Min Act: -0.0000

Data Index: 840837 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.3878. Min Act: -0.0000

Data Index: 201886 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1285576 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.6248. Min Act: -0.0000

Data Index: 243016 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.3659. Min Act: -0.0000

Data Index: 144956 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.5192. Min Act: -0.0000

Data Index: 647710 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 2.1677. Min Range: -2.1677

Max Act: 1.4253. Min Act: -0.0000

Data Index: 36188 (C4 (Web Text))

Max Activating Token Index: 332