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

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

Neuron 4190 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: 2.9531. Min Range: -2.9531

Max Act: 2.9531. Min Act: -0.0000

Data Index: 185897 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 2.9531. Min Range: -2.9531

Max Act: 2.7224. Min Act: -0.0000

Data Index: 841384 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 2.9531. Min Range: -2.9531

Max Act: 2.4183. Min Act: -0.0000

Data Index: 1310677 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 2.9531. Min Range: -2.9531

Max Act: 2.5036. Min Act: -0.0000

Data Index: 689459 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 2.9531. Min Range: -2.9531

Max Act: 2.4897. Min Act: -0.0000

Data Index: 447550 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 2.9531. Min Range: -2.9531

Max Act: 2.1254. Min Act: -0.0000

Data Index: 693176 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 2.9531. Min Range: -2.9531

Max Act: 2.0905. Min Act: -0.0000

Data Index: 187688 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.7781. Min Act: -0.0000

Data Index: 270055 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.6420. Min Act: -0.0000

Data Index: 713018 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.5401. Min Act: -0.0000

Data Index: 777058 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.4173. Min Act: -0.0000

Data Index: 383065 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.8837. Min Act: -0.0000

Data Index: 964657 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.6647. Min Act: -0.0000

Data Index: 542949 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.4598. Min Act: -0.0000

Data Index: 741542 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.5321. Min Act: -0.0000

Data Index: 671134 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.4209. Min Act: -0.0000

Data Index: 238771 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.4382. Min Act: -0.0000

Data Index: 649818 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.3551. Min Act: -0.0000

Data Index: 946457 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.4378. Min Act: -0.0000

Data Index: 964929 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 2.9531. Min Range: -2.9531

Max Act: 1.3429. Min Act: -0.0000

Data Index: 314073 (C4 (Web Text))

Max Activating Token Index: 295