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

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

Neuron 474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4692. Min Act: -0.0000

Data Index: 435397 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4371. Min Act: -0.0000

Data Index: 351173 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4118. Min Act: -0.0000

Data Index: 848870 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3623. Min Act: -0.0000

Data Index: 893968 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3729. Min Act: -0.0000

Data Index: 463994 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1270171 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3070. Min Act: -0.0000

Data Index: 987275 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1054215 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1054523 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2626. Min Act: -0.0000

Data Index: 393642 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2709. Min Act: -0.0000

Data Index: 527614 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1356568 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2821. Min Act: -0.0000

Data Index: 52790 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1211376 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2626. Min Act: -0.0000

Data Index: 244707 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2710. Min Act: -0.0000

Data Index: 718931 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2808. Min Act: -0.0000

Data Index: 615769 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1141060 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1137259 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2492. Min Act: -0.0000

Data Index: 632812 (C4 (Web Text))

Max Activating Token Index: 916