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

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

Neuron 636 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: 3.0353. Min Range: -3.0353

Max Act: 3.0353. Min Act: -0.0001

Data Index: 943292 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.4789. Min Act: -0.0001

Data Index: 860806 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.6883. Min Act: -0.0000

Data Index: 992626 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.6798. Min Act: -0.0001

Data Index: 1035076 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.4968. Min Act: -0.0000

Data Index: 1039317 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.4410. Min Act: -0.0001

Data Index: 659339 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.2523. Min Act: -0.0001

Data Index: 942652 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.2492. Min Act: -0.0000

Data Index: 370112 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.3293. Min Act: -0.0001

Data Index: 858243 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.3064. Min Act: -0.0001

Data Index: 732499 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.6011. Min Act: -0.0000

Data Index: 476385 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.1941. Min Act: -0.0001

Data Index: 684701 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 3.0353. Min Range: -3.0353

Max Act: 1.9656. Min Act: -0.0001

Data Index: 686561 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.2653. Min Act: -0.0001

Data Index: 734359 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.2667. Min Act: -0.0000

Data Index: 836912 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.1314. Min Act: -0.0001

Data Index: 1268500 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.0302. Min Act: -0.0001

Data Index: 1273860 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 3.0353. Min Range: -3.0353

Max Act: 1.9855. Min Act: -0.0001

Data Index: 238993 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 3.0353. Min Range: -3.0353

Max Act: 2.0784. Min Act: -0.0000

Data Index: 252681 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 3.0353. Min Range: -3.0353

Max Act: 1.9664. Min Act: -0.0000

Data Index: 981765 (C4 (Web Text))

Max Activating Token Index: 896