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

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

Neuron 5112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.9326. Min Act: -0.0000

Data Index: 226880 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.8480. Min Act: -0.0000

Data Index: 18036 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.7665. Min Act: -0.0000

Data Index: 216521 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.4730. Min Act: -0.0000

Data Index: 1206468 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.5735. Min Act: -0.0000

Data Index: 629711 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.3304. Min Act: -0.0000

Data Index: 201134 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.4819. Min Act: -0.0000

Data Index: 770118 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.2744. Min Act: -0.0000

Data Index: 1007094 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.2462. Min Act: -0.0000

Data Index: 463379 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.9082. Min Act: -0.0000

Data Index: 429917 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.3329. Min Act: -0.0000

Data Index: 171573 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.2422. Min Act: -0.0000

Data Index: 1037367 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 4.9326. Min Range: -4.9326

Max Act: 4.0356. Min Act: -0.0000

Data Index: 232119 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.8735. Min Act: -0.0000

Data Index: 285285 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.9296. Min Act: -0.0000

Data Index: 763088 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.7280. Min Act: -0.0000

Data Index: 839740 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.8659. Min Act: -0.0000

Data Index: 1262649 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.8615. Min Act: -0.0000

Data Index: 936990 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.5396. Min Act: -0.0000

Data Index: 328893 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 4.9326. Min Range: -4.9326

Max Act: 3.6516. Min Act: -0.0000

Data Index: 21829 (C4 (Web Text))

Max Activating Token Index: 132