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

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

Neuron 3639 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.9825. Min Act: -0.0000

Data Index: 946559 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 5.0350. Min Range: -5.0350

Max Act: 5.0350. Min Act: -0.0000

Data Index: 77889 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.8373. Min Act: -0.0000

Data Index: 334459 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.7093. Min Act: -0.0000

Data Index: 1025436 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.8603. Min Act: -0.0000

Data Index: 451402 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.6235. Min Act: -0.0000

Data Index: 1026090 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.4785. Min Act: -0.0000

Data Index: 428069 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.3308. Min Act: -0.0000

Data Index: 520494 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.5889. Min Act: -0.0000

Data Index: 588436 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.4284. Min Act: -0.0000

Data Index: 129518 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.5823. Min Act: -0.0000

Data Index: 174322 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.5775. Min Act: -0.0000

Data Index: 271651 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.5559. Min Act: -0.0000

Data Index: 840750 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.5694. Min Act: -0.0000

Data Index: 604002 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.3547. Min Act: -0.0000

Data Index: 1242391 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.5211. Min Act: -0.0000

Data Index: 1266390 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.4817. Min Act: -0.0000

Data Index: 136414 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.3167. Min Act: -0.0000

Data Index: 321531 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.2995. Min Act: -0.0000

Data Index: 870954 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 5.0350. Min Range: -5.0350

Max Act: 4.4283. Min Act: -0.0000

Data Index: 431514 (C4 (Web Text))

Max Activating Token Index: 419