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

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

Neuron 630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5639. Min Range: -2.5639

Max Act: 2.4960. Min Act: -0.0000

Data Index: 1124580 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 2.5639. Min Range: -2.5639

Max Act: 2.5639. Min Act: -0.0000

Data Index: 1286710 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 2.5639. Min Range: -2.5639

Max Act: 2.0065. Min Act: -0.0000

Data Index: 59632 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 2.5639. Min Range: -2.5639

Max Act: 2.1077. Min Act: -0.0000

Data Index: 811990 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 2.5639. Min Range: -2.5639

Max Act: 2.0485. Min Act: -0.0000

Data Index: 517013 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.7306. Min Act: -0.0000

Data Index: 54455 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.7656. Min Act: -0.0000

Data Index: 200102 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.6047. Min Act: -0.0000

Data Index: 1270257 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.6295. Min Act: -0.0000

Data Index: 638008 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.6123. Min Act: -0.0000

Data Index: 1106621 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.7335. Min Act: -0.0000

Data Index: 987922 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.6015. Min Act: -0.0000

Data Index: 1166358 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.5105. Min Act: -0.0000

Data Index: 734557 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.5536. Min Act: -0.0000

Data Index: 359558 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1172077 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1268344 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.5874. Min Act: -0.0000

Data Index: 7072 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.4975. Min Act: -0.0000

Data Index: 36664 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.3776. Min Act: -0.0000

Data Index: 204602 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 2.5639. Min Range: -2.5639

Max Act: 1.3496. Min Act: -0.0000

Data Index: 855586 (C4 (Web Text))

Max Activating Token Index: 175