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

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

Neuron 2562 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: 0.8691. Min Range: -0.8691

Max Act: 0.8691. Min Act: 0.0000

Data Index: 1581221 (Python Code)

Max Activating Token Index: 371

Text #1

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1459410 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.6301. Min Act: 0.0000

Data Index: 1603208 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1366552 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5794. Min Act: 0.0000

Data Index: 1537922 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5995. Min Act: 0.0000

Data Index: 1572728 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1407839 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1650684 (Python Code)

Max Activating Token Index: 747

Text #8

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1470684 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.6127. Min Act: 0.0000

Data Index: 1493605 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5630. Min Act: 0.0000

Data Index: 1381916 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5850. Min Act: 0.0000

Data Index: 1452363 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1408376 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5453. Min Act: 0.0000

Data Index: 1421063 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5585. Min Act: 0.0000

Data Index: 1465522 (Python Code)

Max Activating Token Index: 111

Text #15

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1553461 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1486502 (Python Code)

Max Activating Token Index: 835

Text #17

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1564890 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1365114 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 0.8691. Min Range: -0.8691

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1422967 (Python Code)

Max Activating Token Index: 271