Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2628 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0641. Min Range: -2.0641

Max Act: 2.0641. Min Act: -0.0000

Data Index: 470508 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.6577. Min Act: -0.0000

Data Index: 507310 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.4823. Min Act: -0.0000

Data Index: 640645 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.6500. Min Act: -0.0000

Data Index: 1268679 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.6572. Min Act: -0.0000

Data Index: 940850 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.4137. Min Act: -0.0000

Data Index: 748202 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1268004 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1273753 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.3313. Min Act: -0.0000

Data Index: 178933 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.2206. Min Act: -0.0000

Data Index: 450430 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.2672. Min Act: -0.0000

Data Index: 369375 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.1828. Min Act: -0.0000

Data Index: 415779 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1201085 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.1864. Min Act: -0.0000

Data Index: 10775 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.0892. Min Act: -0.0000

Data Index: 611159 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1171521 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.1525. Min Act: -0.0000

Data Index: 865966 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.1478. Min Act: -0.0000

Data Index: 575242 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.4799. Min Act: -0.0000

Data Index: 531944 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1061923 (C4 (Web Text))

Max Activating Token Index: 417