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

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

Neuron 3453 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.4756. Min Act: -0.0001

Data Index: 369311 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.2948. Min Act: -0.0001

Data Index: 25772 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.2403. Min Act: -0.0001

Data Index: 97229 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.1190. Min Act: -0.0001

Data Index: 175356 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.1299. Min Act: -0.0000

Data Index: 158746 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0964. Min Act: -0.0001

Data Index: 796138 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0533. Min Act: -0.0001

Data Index: 1330680 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0181. Min Act: -0.0001

Data Index: 536035 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0007. Min Act: -0.0001

Data Index: 1036978 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0062. Min Act: -0.0001

Data Index: 1135131 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0256. Min Act: -0.0001

Data Index: 349477 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0452. Min Act: -0.0001

Data Index: 1133209 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9830. Min Act: -0.0001

Data Index: 564792 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9923. Min Act: -0.0001

Data Index: 9936 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9584. Min Act: -0.0001

Data Index: 336050 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9957. Min Act: -0.0001

Data Index: 340026 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9599. Min Act: -0.0001

Data Index: 1005623 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9195. Min Act: -0.0001

Data Index: 1177609 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9506. Min Act: -0.0001

Data Index: 6115 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9075. Min Act: -0.0001

Data Index: 1021345 (C4 (Web Text))

Max Activating Token Index: 74