Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.6531. Min Act: -0.0000

Data Index: 1532059 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.5593. Min Act: -0.0000

Data Index: 373351 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.3238. Min Act: -0.0000

Data Index: 369372 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1367870 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1496468 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1592198 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1448517 (Python Code)

Max Activating Token Index: 563

Text #7

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1317143 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1450045 (Python Code)

Max Activating Token Index: 69

Text #9

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1415827 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1425583 (Python Code)

Max Activating Token Index: 913

Text #11

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1554851 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1533485 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.1983. Min Act: -0.0000

Data Index: 612342 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1541744 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1465808 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.0928. Min Act: -0.0000

Data Index: 929562 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1379200 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1626029 (Python Code)

Max Activating Token Index: 346

Text #19

Max Range: 1.6531. Min Range: -1.6531

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1533831 (Python Code)

Max Activating Token Index: 651