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

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

Neuron 1467 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.7140. Min Act: -0.0000

Data Index: 674759 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.7082. Min Act: -0.0000

Data Index: 298076 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6191. Min Act: -0.0000

Data Index: 581991 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1076463 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6432. Min Act: -0.0000

Data Index: 414884 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6450. Min Act: -0.0000

Data Index: 455696 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5793. Min Act: -0.0000

Data Index: 661316 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1097309 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5458. Min Act: -0.0000

Data Index: 231267 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4791. Min Act: -0.0000

Data Index: 10970 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1193093 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5267. Min Act: -0.0000

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1134765 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4336. Min Act: -0.0000

Data Index: 342630 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4893. Min Act: -0.0000

Data Index: 394064 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4779. Min Act: -0.0000

Data Index: 679037 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4647. Min Act: -0.0000

Data Index: 717954 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1205378 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5026. Min Act: -0.0000

Data Index: 100751 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4061. Min Act: -0.0000

Data Index: 509138 (C4 (Web Text))

Max Activating Token Index: 1016