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

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

Neuron 583 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.8435. Min Act: -0.0001

Data Index: 247204 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7986. Min Act: -0.0001

Data Index: 1310477 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7942. Min Act: -0.0001

Data Index: 993711 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7686. Min Act: -0.0001

Data Index: 285177 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7626. Min Act: -0.0001

Data Index: 214450 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1103783 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7494. Min Act: -0.0001

Data Index: 90652 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7249. Min Act: -0.0001

Data Index: 151992 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7332. Min Act: -0.0001

Data Index: 1300085 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7069. Min Act: -0.0001

Data Index: 119631 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7173. Min Act: -0.0001

Data Index: 29007 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7026. Min Act: -0.0001

Data Index: 754792 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.7068. Min Act: -0.0001

Data Index: 1021960 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6860. Min Act: -0.0001

Data Index: 571140 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6849. Min Act: -0.0001

Data Index: 1170441 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6793. Min Act: -0.0001

Data Index: 661015 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1064430 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6983. Min Act: -0.0001

Data Index: 1272270 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6882. Min Act: -0.0001

Data Index: 425380 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.8435. Min Range: -0.8435

Max Act: 0.6455. Min Act: -0.0001

Data Index: 30057 (C4 (Web Text))

Max Activating Token Index: 785