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

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

Neuron 2549 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6440. Min Range: -4.6440

Max Act: 4.6440. Min Act: -0.0000

Data Index: 332510 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 4.6440. Min Range: -4.6440

Max Act: 4.3606. Min Act: -0.0000

Data Index: 138169 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 4.6440. Min Range: -4.6440

Max Act: 4.4154. Min Act: -0.0000

Data Index: 13286 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.7621. Min Act: -0.0000

Data Index: 832413 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 4.6440. Min Range: -4.6440

Max Act: 4.0705. Min Act: -0.0000

Data Index: 1137184 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.9988. Min Act: -0.0000

Data Index: 810160 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.7701. Min Act: -0.0000

Data Index: 371618 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.7361. Min Act: -0.0000

Data Index: 620099 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.6078. Min Act: -0.0000

Data Index: 37365 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.5259. Min Act: -0.0000

Data Index: 789789 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.3211. Min Act: -0.0000

Data Index: 1285183 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.7544. Min Act: -0.0000

Data Index: 229222 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.5393. Min Act: -0.0000

Data Index: 821337 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.6510. Min Act: -0.0000

Data Index: 37276 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.4614. Min Act: -0.0000

Data Index: 60083 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.4642. Min Act: -0.0000

Data Index: 544099 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.4134. Min Act: -0.0000

Data Index: 305800 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.4093. Min Act: -0.0000

Data Index: 803384 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.0516. Min Act: -0.0000

Data Index: 883876 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 4.6440. Min Range: -4.6440

Max Act: 3.1345. Min Act: -0.0000

Data Index: 354421 (C4 (Web Text))

Max Activating Token Index: 902