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

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

Neuron 3327 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.9120. Min Act: -0.0000

Data Index: 1207467 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.8588. Min Act: -0.0000

Data Index: 238515 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.7903. Min Act: -0.0000

Data Index: 545266 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.7911. Min Act: -0.0000

Data Index: 1540305 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6564. Min Act: -0.0000

Data Index: 186834 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.8131. Min Act: -0.0000

Data Index: 1430103 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.4986. Min Act: -0.0000

Data Index: 295698 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.3111. Min Act: -0.0000

Data Index: 1427040 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6041. Min Act: -0.0000

Data Index: 428009 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6020. Min Act: -0.0000

Data Index: 1498729 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.2722. Min Act: -0.0000

Data Index: 1210165 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.4093. Min Act: -0.0000

Data Index: 1325532 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6434. Min Act: -0.0000

Data Index: 792154 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.0611. Min Act: -0.0000

Data Index: 1548578 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6073. Min Act: -0.0000

Data Index: 1634774 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.3988. Min Act: -0.0000

Data Index: 629130 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.5289. Min Act: -0.0000

Data Index: 1169605 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.3429. Min Act: -0.0000

Data Index: 288682 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.1897. Min Act: -0.0000

Data Index: 1244457 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.4315. Min Act: -0.0000

Data Index: 1227755 (C4 (Web Text))

Max Activating Token Index: 286