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

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

Neuron 4480 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.7642. Min Act: -0.0000

Data Index: 1060806 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.5572. Min Act: -0.0000

Data Index: 419897 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.4329. Min Act: -0.0000

Data Index: 515164 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.4285. Min Act: -0.0000

Data Index: 268451 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3382. Min Act: -0.0000

Data Index: 865654 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3913. Min Act: -0.0000

Data Index: 707058 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3430. Min Act: -0.0000

Data Index: 893640 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3089. Min Act: -0.0000

Data Index: 529302 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1320518 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2510. Min Act: -0.0000

Data Index: 49202 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1064368 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1197546 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2070. Min Act: -0.0000

Data Index: 308478 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.1893. Min Act: -0.0000

Data Index: 107633 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3049. Min Act: -0.0000

Data Index: 20798 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.1740. Min Act: -0.0000

Data Index: 297826 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.1686. Min Act: -0.0000

Data Index: 291531 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.1562. Min Act: -0.0000

Data Index: 772475 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1177156 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.0579. Min Act: -0.0000

Data Index: 79989 (C4 (Web Text))

Max Activating Token Index: 739