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

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

Neuron 1926 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6964. Min Act: -0.0000

Data Index: 401319 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6884. Min Act: -0.0000

Data Index: 570305 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6391. Min Act: -0.0000

Data Index: 42445 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1156252 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5610. Min Act: -0.0001

Data Index: 817372 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5577. Min Act: -0.0000

Data Index: 655385 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5502. Min Act: -0.0000

Data Index: 294849 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5534. Min Act: -0.0001

Data Index: 733726 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5660. Min Act: -0.0000

Data Index: 78159 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5241. Min Act: -0.0000

Data Index: 812832 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5423. Min Act: -0.0000

Data Index: 954545 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5362. Min Act: -0.0000

Data Index: 496119 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5405. Min Act: -0.0000

Data Index: 705965 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5180. Min Act: -0.0000

Data Index: 211036 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5202. Min Act: -0.0000

Data Index: 217481 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5171. Min Act: -0.0000

Data Index: 826462 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5083. Min Act: -0.0000

Data Index: 973635 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1210059 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5140. Min Act: -0.0000

Data Index: 964818 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.4972. Min Act: -0.0000

Data Index: 187072 (C4 (Web Text))

Max Activating Token Index: 1015