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

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

Neuron 2348 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4096. Min Range: -7.4096

Max Act: 7.4096. Min Act: -0.0001

Data Index: 222509 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 7.4096. Min Range: -7.4096

Max Act: 7.1697. Min Act: -0.0001

Data Index: 1140578 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 7.4096. Min Range: -7.4096

Max Act: 6.3932. Min Act: -0.0001

Data Index: 819866 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 7.4096. Min Range: -7.4096

Max Act: 6.2391. Min Act: -0.0001

Data Index: 989381 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 7.4096. Min Range: -7.4096

Max Act: 6.2736. Min Act: -0.0001

Data Index: 12462 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 7.4096. Min Range: -7.4096

Max Act: 6.2300. Min Act: -0.0001

Data Index: 13769 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.6631. Min Act: -0.0001

Data Index: 839849 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 7.4096. Min Range: -7.4096

Max Act: 6.1923. Min Act: -0.0001

Data Index: 693270 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.9807. Min Act: -0.0001

Data Index: 466035 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.9405. Min Act: -0.0001

Data Index: 18408 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.6759. Min Act: -0.0001

Data Index: 227350 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.4632. Min Act: -0.0001

Data Index: 279676 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.6697. Min Act: -0.0001

Data Index: 1358433 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.8475. Min Act: -0.0001

Data Index: 1310061 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.5923. Min Act: -0.0001

Data Index: 664869 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.5156. Min Act: -0.0001

Data Index: 1217503 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.3065. Min Act: -0.0001

Data Index: 1212572 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.4266. Min Act: -0.0000

Data Index: 630544 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.4350. Min Act: -0.0001

Data Index: 1339321 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 7.4096. Min Range: -7.4096

Max Act: 5.9084. Min Act: -0.0001

Data Index: 379664 (C4 (Web Text))

Max Activating Token Index: 943