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

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

Neuron 4644 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.6927. Min Act: -0.0000

Data Index: 49937 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.5026. Min Act: -0.0000

Data Index: 574728 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.3823. Min Act: -0.0000

Data Index: 314769 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.4451. Min Act: -0.0000

Data Index: 561290 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.5305. Min Act: -0.0000

Data Index: 1136385 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.3934. Min Act: -0.0000

Data Index: 356189 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.4874. Min Act: -0.0000

Data Index: 1305458 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.3270. Min Act: -0.0000

Data Index: 498945 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.1735. Min Act: -0.0000

Data Index: 877141 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.2985. Min Act: -0.0000

Data Index: 353724 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.2872. Min Act: -0.0000

Data Index: 20354 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.1792. Min Act: -0.0000

Data Index: 1024676 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.0678. Min Act: -0.0000

Data Index: 955627 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.0612. Min Act: -0.0000

Data Index: 54430 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.0516. Min Act: -0.0000

Data Index: 232992 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.2734. Min Act: -0.0000

Data Index: 1296939 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.1621. Min Act: -0.0000

Data Index: 28121 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.1484. Min Act: -0.0000

Data Index: 389953 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.6927. Min Range: -2.6927

Max Act: 2.0217. Min Act: -0.0000

Data Index: 850421 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 2.6927. Min Range: -2.6927

Max Act: 1.9177. Min Act: -0.0000

Data Index: 161164 (C4 (Web Text))

Max Activating Token Index: 245