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

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

Neuron 4193 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.7362. Min Act: -0.0000

Data Index: 546413 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6942. Min Act: -0.0000

Data Index: 481179 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6449. Min Act: -0.0000

Data Index: 739900 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6686. Min Act: -0.0000

Data Index: 591889 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6938. Min Act: -0.0000

Data Index: 729577 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6900. Min Act: -0.0000

Data Index: 645703 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6488. Min Act: -0.0000

Data Index: 276289 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6152. Min Act: -0.0000

Data Index: 984016 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1102685 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6050. Min Act: -0.0000

Data Index: 465741 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1232378 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6169. Min Act: -0.0000

Data Index: 533556 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1068324 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5947. Min Act: -0.0000

Data Index: 367759 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1023670 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1013520 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1048570 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1295246 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5518. Min Act: -0.0000

Data Index: 620228 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.7362. Min Range: -0.7362

Max Act: 0.5694. Min Act: -0.0000

Data Index: 784401 (C4 (Web Text))

Max Activating Token Index: 782