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

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

Neuron 3457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.7471. Min Act: -0.0000

Data Index: 136718 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.6262. Min Act: -0.0000

Data Index: 1299113 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.6020. Min Act: -0.0000

Data Index: 1240691 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.5153. Min Act: -0.0000

Data Index: 1129069 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.4691. Min Act: -0.0000

Data Index: 94037 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.5935. Min Act: -0.0000

Data Index: 22776 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.4525. Min Act: -0.0000

Data Index: 608575 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.4429. Min Act: -0.0000

Data Index: 780247 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.3254. Min Act: -0.0000

Data Index: 236391 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.4488. Min Act: -0.0000

Data Index: 1130363 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.6714. Min Act: -0.0000

Data Index: 709736 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.5247. Min Act: -0.0000

Data Index: 807113 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.3939. Min Act: -0.0000

Data Index: 594867 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.3835. Min Act: -0.0000

Data Index: 58977 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.3792. Min Act: -0.0000

Data Index: 916616 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.4776. Min Act: -0.0000

Data Index: 1225214 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.3467. Min Act: -0.0000

Data Index: 1328370 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.4493. Min Act: -0.0000

Data Index: 370353 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.3036. Min Act: -0.0000

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 2.7471. Min Range: -2.7471

Max Act: 2.1843. Min Act: -0.0000

Data Index: 272283 (C4 (Web Text))

Max Activating Token Index: 804