Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2858 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1344935 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0756. Min Act: -0.0001

Data Index: 405342 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0626. Min Act: -0.0001

Data Index: 773694 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0656. Min Act: -0.0001

Data Index: 269825 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1295823 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0559. Min Act: -0.0001

Data Index: 463066 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1185128 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0526. Min Act: -0.0001

Data Index: 299509 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0477. Min Act: -0.0001

Data Index: 700118 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0486. Min Act: -0.0001

Data Index: 538931 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0467. Min Act: -0.0001

Data Index: 680548 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1248359 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0462. Min Act: -0.0001

Data Index: 839363 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0445. Min Act: -0.0001

Data Index: 787343 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1305940 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0438. Min Act: -0.0001

Data Index: 875050 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0440. Min Act: -0.0001

Data Index: 130177 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0439. Min Act: -0.0001

Data Index: 176621 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0453. Min Act: -0.0001

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1055008 (C4 (Web Text))

Max Activating Token Index: 276