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

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

Neuron 1967 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.2674. Min Act: -0.0000

Data Index: 1054362 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.2441. Min Act: -0.0000

Data Index: 126888 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.1011. Min Act: -0.0000

Data Index: 1202236 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.1275. Min Act: -0.0000

Data Index: 852070 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.9825. Min Act: -0.0000

Data Index: 260388 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.0482. Min Act: -0.0000

Data Index: 695455 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.0534. Min Act: -0.0001

Data Index: 906419 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.0140. Min Act: -0.0000

Data Index: 295908 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.9241. Min Act: -0.0000

Data Index: 1220288 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.9106. Min Act: -0.0000

Data Index: 720963 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.9884. Min Act: -0.0000

Data Index: 494969 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.8338. Min Act: -0.0000

Data Index: 870373 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.9355. Min Act: -0.0000

Data Index: 1290912 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.8570. Min Act: -0.0000

Data Index: 1269555 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.8952. Min Act: -0.0000

Data Index: 719439 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.9015. Min Act: -0.0000

Data Index: 1163153 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.8512. Min Act: -0.0000

Data Index: 311032 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 2.2674. Min Range: -2.2674

Max Act: 2.0622. Min Act: -0.0000

Data Index: 633263 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.8503. Min Act: -0.0000

Data Index: 1256545 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 2.2674. Min Range: -2.2674

Max Act: 1.9631. Min Act: -0.0000

Data Index: 1189218 (C4 (Web Text))

Max Activating Token Index: 862