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

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

Neuron 2141 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.8174. Min Act: -0.0000

Data Index: 57506 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6889. Min Act: -0.0000

Data Index: 615567 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1461256 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6352. Min Act: -0.0000

Data Index: 246770 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6275. Min Act: -0.0001

Data Index: 271883 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6228. Min Act: -0.0001

Data Index: 1489995 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6027. Min Act: -0.0001

Data Index: 1437525 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1414765 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5995. Min Act: -0.0000

Data Index: 400346 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5555. Min Act: -0.0000

Data Index: 571929 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5547. Min Act: -0.0001

Data Index: 1649556 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5535. Min Act: -0.0000

Data Index: 596568 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5598. Min Act: -0.0001

Data Index: 1596189 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1056073 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1407581 (Python Code)

Max Activating Token Index: 836

Text #15

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5353. Min Act: -0.0001

Data Index: 915472 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5331. Min Act: -0.0001

Data Index: 1372745 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5452. Min Act: -0.0000

Data Index: 319643 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5579. Min Act: -0.0001

Data Index: 799173 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.8174. Min Range: -0.8174

Max Act: 0.5363. Min Act: -0.0000

Data Index: 957256 (C4 (Web Text))

Max Activating Token Index: 148