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

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

Neuron 3938 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: 0.6729. Min Range: -0.6729

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1206 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.6444. Min Act: -0.0000

Data Index: 758403 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.6162. Min Act: -0.0000

Data Index: 257474 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1109361 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.6109. Min Act: -0.0000

Data Index: 126262 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1052673 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5518. Min Act: -0.0000

Data Index: 544778 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5315. Min Act: -0.0000

Data Index: 329166 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5456. Min Act: -0.0000

Data Index: 334331 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1309262 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5332. Min Act: -0.0000

Data Index: 728962 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5310. Min Act: -0.0000

Data Index: 577190 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5273. Min Act: -0.0000

Data Index: 337449 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1144138 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1064005 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.4980. Min Act: -0.0000

Data Index: 390054 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.5007. Min Act: -0.0000

Data Index: 215791 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1241339 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1148863 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.6729. Min Range: -0.6729

Max Act: 0.4922. Min Act: -0.0000

Data Index: 511005 (C4 (Web Text))

Max Activating Token Index: 465