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

Dataset: The Pile

Neuron 1837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.8628. Min Act: -0.0000

Data Index: 7182 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1918278 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1400848 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1840083 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1761317 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1802374 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1978137 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1047023 (The Pile)

Max Activating Token Index: 389

Text #8

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6011. Min Act: -0.0000

Data Index: 678438 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6559. Min Act: -0.0000

Data Index: 794166 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6143. Min Act: -0.0000

Data Index: 365241 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6381. Min Act: -0.0000

Data Index: 464775 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5822. Min Act: -0.0000

Data Index: 368971 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5965. Min Act: -0.0000

Data Index: 463685 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1126289 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5631. Min Act: -0.0000

Data Index: 615382 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5680. Min Act: -0.0000

Data Index: 716820 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5399. Min Act: -0.0000

Data Index: 681565 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1259916 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.5262. Min Act: -0.0000

Data Index: 469029 (The Pile)

Max Activating Token Index: 889