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

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

Neuron 1833 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1933. Min Range: -3.1933

Max Act: 3.0685. Min Act: -0.0000

Data Index: 836441 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 3.1933. Min Range: -3.1933

Max Act: 3.1877. Min Act: -0.0000

Data Index: 111950 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 3.1933. Min Range: -3.1933

Max Act: 3.1933. Min Act: -0.0000

Data Index: 186316 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 3.1933. Min Range: -3.1933

Max Act: 3.1674. Min Act: -0.0000

Data Index: 1098879 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.9539. Min Act: -0.0000

Data Index: 399995 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.8966. Min Act: -0.0000

Data Index: 602009 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.7984. Min Act: -0.0000

Data Index: 1045822 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.8288. Min Act: -0.0000

Data Index: 772229 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.8371. Min Act: -0.0000

Data Index: 185838 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.8291. Min Act: -0.0000

Data Index: 1294186 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.8212. Min Act: -0.0000

Data Index: 940518 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.7960. Min Act: -0.0000

Data Index: 767604 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.6319. Min Act: -0.0000

Data Index: 1262033 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.7145. Min Act: -0.0000

Data Index: 253387 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.6990. Min Act: -0.0000

Data Index: 50259 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.7038. Min Act: -0.0000

Data Index: 559941 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.6822. Min Act: -0.0000

Data Index: 989141 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.6808. Min Act: -0.0000

Data Index: 1391941 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.6556. Min Act: -0.0000

Data Index: 1035694 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 3.1933. Min Range: -3.1933

Max Act: 2.7763. Min Act: -0.0000

Data Index: 411282 (C4 (Web Text))

Max Activating Token Index: 984