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

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

Neuron 2804 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1161271 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1614491 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1527963 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1538679 (Python Code)

Max Activating Token Index: 641

Text #4

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1601456 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1430804 (Python Code)

Max Activating Token Index: 630

Text #6

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1384809 (Python Code)

Max Activating Token Index: 877

Text #7

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1282181 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1594563 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1453780 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3592. Min Act: -0.0000

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3678. Min Act: -0.0000

Data Index: 534482 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3774. Min Act: -0.0000

Data Index: 466198 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1646821 (Python Code)

Max Activating Token Index: 544

Text #14

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1493033 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1404713 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1518332 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3593. Min Act: -0.0000

Data Index: 702837 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1078840 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.3338. Min Act: -0.0000

Data Index: 56818 (C4 (Web Text))

Max Activating Token Index: 34