Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3035 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1580. Min Range: -3.1580

Max Act: 3.0869. Min Act: -0.0001

Data Index: 570529 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 3.1580. Min Range: -3.1580

Max Act: 3.1580. Min Act: -0.0001

Data Index: 289274 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.6401. Min Act: -0.0001

Data Index: 903867 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.0767. Min Act: -0.0001

Data Index: 415590 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.3161. Min Act: -0.0001

Data Index: 1097916 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.2370. Min Act: -0.0001

Data Index: 745469 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.3632. Min Act: -0.0001

Data Index: 1006616 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.5099. Min Act: -0.0002

Data Index: 236474 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.1154. Min Act: -0.0001

Data Index: 731033 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.0887. Min Act: -0.0001

Data Index: 895041 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.2048. Min Act: -0.0001

Data Index: 645749 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.3151. Min Act: -0.0001

Data Index: 845246 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.1960. Min Act: -0.0001

Data Index: 1319565 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.2930. Min Act: -0.0002

Data Index: 488940 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.0474. Min Act: -0.0001

Data Index: 302298 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.1244. Min Act: -0.0002

Data Index: 1114217 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.5024. Min Act: -0.0002

Data Index: 973656 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.3779. Min Act: -0.0001

Data Index: 221136 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.2202. Min Act: -0.0002

Data Index: 322678 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 3.1580. Min Range: -3.1580

Max Act: 2.4175. Min Act: -0.0001

Data Index: 1269245 (C4 (Web Text))

Max Activating Token Index: 538