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

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

Neuron 2583 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2120. Min Range: -2.2120

Max Act: 2.2120. Min Act: -0.0000

Data Index: 167137 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.8220. Min Act: -0.0000

Data Index: 723891 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.9559. Min Act: -0.0000

Data Index: 167962 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1093790 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.8080. Min Act: -0.0000

Data Index: 496162 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.7752. Min Act: -0.0000

Data Index: 667773 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.7368. Min Act: -0.0000

Data Index: 315372 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.9103. Min Act: -0.0000

Data Index: 643188 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.6872. Min Act: -0.0000

Data Index: 1611991 (Python Code)

Max Activating Token Index: 773

Text #9

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.5650. Min Act: -0.0000

Data Index: 823394 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.6087. Min Act: -0.0000

Data Index: 239297 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.5414. Min Act: -0.0000

Data Index: 475650 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.4823. Min Act: -0.0000

Data Index: 1560114 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1595132 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.5595. Min Act: -0.0000

Data Index: 367536 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1587701 (Python Code)

Max Activating Token Index: 601

Text #16

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1630343 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1389021 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.5684. Min Act: -0.0000

Data Index: 733491 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.2120. Min Range: -2.2120

Max Act: 1.6859. Min Act: -0.0000

Data Index: 165729 (C4 (Web Text))

Max Activating Token Index: 866