Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2016 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6514. Min Act: -0.0000

Data Index: 367857 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6310. Min Act: -0.0000

Data Index: 196585 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5813. Min Act: -0.0000

Data Index: 897217 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5926. Min Act: -0.0000

Data Index: 983836 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5356. Min Act: -0.0000

Data Index: 485404 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5594. Min Act: -0.0000

Data Index: 58231 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5706. Min Act: -0.0000

Data Index: 269459 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5676. Min Act: -0.0000

Data Index: 670211 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5487. Min Act: -0.0000

Data Index: 128347 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5364. Min Act: -0.0000

Data Index: 570912 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5550. Min Act: -0.0000

Data Index: 277845 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5261. Min Act: -0.0000

Data Index: 18214 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1140638 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1353021 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1015678 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1142534 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1023281 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1166316 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5100. Min Act: -0.0000

Data Index: 990559 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1039338 (C4 (Web Text))

Max Activating Token Index: 32