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

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

Neuron 4266 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: 0.9426. Min Range: -0.9426

Max Act: 0.9426. Min Act: -0.0000

Data Index: 830518 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1315293 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8527. Min Act: -0.0000

Data Index: 948774 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8464. Min Act: -0.0000

Data Index: 75843 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8159. Min Act: -0.0000

Data Index: 899257 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.8157. Min Act: -0.0000

Data Index: 43236 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1035227 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1004699 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1047849 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7476. Min Act: -0.0000

Data Index: 822463 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7381. Min Act: -0.0000

Data Index: 885538 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7564. Min Act: -0.0000

Data Index: 337931 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1171359 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6776. Min Act: -0.0000

Data Index: 760037 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6772. Min Act: -0.0000

Data Index: 984913 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6947. Min Act: -0.0000

Data Index: 824572 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6491. Min Act: -0.0000

Data Index: 303537 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6493. Min Act: -0.0000

Data Index: 273680 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6576. Min Act: -0.0000

Data Index: 427972 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.9426. Min Range: -0.9426

Max Act: 0.6531. Min Act: -0.0000

Data Index: 382954 (C4 (Web Text))

Max Activating Token Index: 576