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

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

Neuron 5009 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.8759. Min Act: -0.0000

Data Index: 287449 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 2.0411. Min Range: -2.0411

Max Act: 2.0411. Min Act: -0.0000

Data Index: 1017258 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.7989. Min Act: -0.0000

Data Index: 1118777 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.9933. Min Act: -0.0000

Data Index: 1284935 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.8979. Min Act: -0.0000

Data Index: 263533 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.6702. Min Act: -0.0000

Data Index: 69567 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.6296. Min Act: -0.0000

Data Index: 385408 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.6111. Min Act: -0.0000

Data Index: 578609 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.6142. Min Act: -0.0000

Data Index: 340258 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1150346 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4942. Min Act: -0.0000

Data Index: 1311335 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4480. Min Act: -0.0000

Data Index: 796497 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4481. Min Act: -0.0000

Data Index: 141604 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4733. Min Act: -0.0000

Data Index: 515666 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.5425. Min Act: -0.0000

Data Index: 895450 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4748. Min Act: -0.0000

Data Index: 947054 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4599. Min Act: -0.0000

Data Index: 522400 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1057342 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1152184 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 2.0411. Min Range: -2.0411

Max Act: 1.4686. Min Act: -0.0000

Data Index: 441429 (C4 (Web Text))

Max Activating Token Index: 437