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

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

Neuron 2275 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3317. Min Act: -0.0000

Data Index: 509223 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3246. Min Act: -0.0000

Data Index: 103578 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3177. Min Act: -0.0001

Data Index: 582440 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1130127 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2817. Min Act: -0.0001

Data Index: 132008 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3008. Min Act: -0.0001

Data Index: 977170 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2830. Min Act: -0.0000

Data Index: 564320 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1256265 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2830. Min Act: -0.0000

Data Index: 627291 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1251213 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2692. Min Act: -0.0001

Data Index: 452468 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2623. Min Act: -0.0001

Data Index: 335045 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2497. Min Act: -0.0001

Data Index: 153859 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2580. Min Act: -0.0001

Data Index: 175812 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2454. Min Act: -0.0000

Data Index: 914626 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1250596 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2518. Min Act: -0.0001

Data Index: 409518 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1254261 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1231230 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2366. Min Act: -0.0001

Data Index: 779060 (C4 (Web Text))

Max Activating Token Index: 900