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

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

Neuron 3962 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: 0.4462. Min Range: -0.4462

Max Act: 0.4462. Min Act: -0.0000

Data Index: 742955 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4316. Min Act: -0.0000

Data Index: 256002 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4106. Min Act: -0.0000

Data Index: 676337 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1097481 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3705. Min Act: -0.0000

Data Index: 979203 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3470. Min Act: -0.0000

Data Index: 394938 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1075490 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1023268 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1159413 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2929. Min Act: -0.0000

Data Index: 234105 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3040. Min Act: -0.0000

Data Index: 851416 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3073. Min Act: -0.0000

Data Index: 103224 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2668. Min Act: -0.0000

Data Index: 691093 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1173300 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2575. Min Act: -0.0000

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1250122 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2511. Min Act: -0.0000

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2416. Min Act: -0.0000

Data Index: 858230 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.2362. Min Act: -0.0000

Data Index: 770387 (C4 (Web Text))

Max Activating Token Index: 563