Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2089 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3841. Min Range: -1.3841

Max Act: 1.3841. Min Act: -0.0001

Data Index: 1217943 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1221707 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.8538. Min Act: -0.0000

Data Index: 779912 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1573738 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7777. Min Act: -0.0001

Data Index: 1646596 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1018491 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1188776 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7373. Min Act: -0.0001

Data Index: 1216373 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7599. Min Act: -0.0001

Data Index: 758209 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7066. Min Act: -0.0001

Data Index: 845381 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7125. Min Act: -0.0000

Data Index: 921189 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7034. Min Act: -0.0000

Data Index: 380090 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1345575 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7410. Min Act: -0.0001

Data Index: 613774 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.6907. Min Act: -0.0001

Data Index: 137755 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7130. Min Act: -0.0001

Data Index: 1464120 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7086. Min Act: -0.0000

Data Index: 10091 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1328125 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1420215 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 1.3841. Min Range: -1.3841

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1229445 (C4 (Web Text))

Max Activating Token Index: 853