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

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

Neuron 346 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: 2.1913. Min Range: -2.1913

Max Act: 2.1913. Min Act: -0.0000

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.9809. Min Act: -0.0000

Data Index: 1532042 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.5831. Min Act: -0.0000

Data Index: 1505480 (Python Code)

Max Activating Token Index: 300

Text #3

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.3212. Min Act: -0.0000

Data Index: 1481986 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.4881. Min Act: -0.0000

Data Index: 930245 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1385402 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.4481. Min Act: -0.0000

Data Index: 739275 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1443319 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.4293. Min Act: -0.0000

Data Index: 356428 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1488905 (Python Code)

Max Activating Token Index: 797

Text #10

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1645734 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1640123 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1423732 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.1406. Min Act: -0.0000

Data Index: 765597 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1127649 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.2153. Min Act: -0.0000

Data Index: 206694 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.0935. Min Act: -0.0000

Data Index: 671847 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1309497 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.1990. Min Act: -0.0000

Data Index: 787253 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.1913. Min Range: -2.1913

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1048223 (C4 (Web Text))

Max Activating Token Index: 116