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

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

Neuron 3745 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.3081. Min Act: -0.0000

Data Index: 79369 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1046. Min Act: -0.0000

Data Index: 585113 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2463. Min Act: -0.0000

Data Index: 805249 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0963. Min Act: -0.0000

Data Index: 558441 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.3943. Min Act: -0.0000

Data Index: 788092 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2184. Min Act: -0.0000

Data Index: 778112 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2110. Min Act: -0.0000

Data Index: 1028577 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0176. Min Act: -0.0000

Data Index: 623944 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1219. Min Act: -0.0000

Data Index: 24506 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9572. Min Act: -0.0000

Data Index: 6789 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1021. Min Act: -0.0000

Data Index: 631353 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1029. Min Act: -0.0000

Data Index: 262959 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.1040. Min Act: -0.0000

Data Index: 1267977 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0858. Min Act: -0.0000

Data Index: 331107 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2018. Min Act: -0.0000

Data Index: 1297476 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0466. Min Act: -0.0000

Data Index: 906637 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9635. Min Act: -0.0000

Data Index: 266298 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9315. Min Act: -0.0000

Data Index: 1297573 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.7669. Min Act: -0.0000

Data Index: 374887 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.6336. Min Act: -0.0000

Data Index: 774298 (C4 (Web Text))

Max Activating Token Index: 330