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

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

Neuron 1450 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1933. Min Act: -0.0001

Data Index: 435949 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1619. Min Act: -0.0001

Data Index: 742786 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1520. Min Act: -0.0001

Data Index: 27227 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1388. Min Act: -0.0001

Data Index: 112364 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1413. Min Act: -0.0001

Data Index: 941104 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1379. Min Act: -0.0001

Data Index: 216337 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1098993 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1301. Min Act: -0.0001

Data Index: 895858 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1209. Min Act: -0.0001

Data Index: 804884 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1320. Min Act: -0.0001

Data Index: 492412 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1006962 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1171742 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1272438 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1227. Min Act: -0.0001

Data Index: 98528 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1215606 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1164. Min Act: -0.0001

Data Index: 379141 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1229. Min Act: -0.0001

Data Index: 731273 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1070794 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1105882 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1488355 (Python Code)

Max Activating Token Index: 530