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

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

Neuron 1827 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: 4.4887. Min Range: -4.4887

Max Act: 4.4887. Min Act: -0.0000

Data Index: 673312 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 4.4887. Min Range: -4.4887

Max Act: 4.1196. Min Act: -0.0000

Data Index: 264880 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.4408. Min Act: -0.0000

Data Index: 640356 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.9582. Min Act: -0.0000

Data Index: 926441 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 4.4887. Min Range: -4.4887

Max Act: 4.0278. Min Act: -0.0000

Data Index: 725826 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.5725. Min Act: -0.0000

Data Index: 1234186 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.7601. Min Act: -0.0000

Data Index: 54760 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.1169. Min Act: -0.0000

Data Index: 669267 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.0986. Min Act: -0.0000

Data Index: 568244 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.7085. Min Act: -0.0000

Data Index: 535978 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.3472. Min Act: -0.0000

Data Index: 1346363 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.6598. Min Act: -0.0000

Data Index: 1308024 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.7571. Min Act: -0.0000

Data Index: 191414 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.3854. Min Act: -0.0000

Data Index: 84997 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.5253. Min Act: -0.0000

Data Index: 1128087 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.8011. Min Act: -0.0000

Data Index: 188754 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.3238. Min Act: -0.0000

Data Index: 898987 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.4946. Min Act: -0.0000

Data Index: 1149786 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.2960. Min Act: -0.0000

Data Index: 1000907 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 4.4887. Min Range: -4.4887

Max Act: 3.4542. Min Act: -0.0000

Data Index: 341351 (C4 (Web Text))

Max Activating Token Index: 864