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

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

Neuron 4340 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.7106. Min Act: -0.0001

Data Index: 761412 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.6367. Min Act: -0.0001

Data Index: 937560 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.5084. Min Act: -0.0001

Data Index: 243676 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.4472. Min Act: -0.0001

Data Index: 741934 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3631. Min Act: -0.0001

Data Index: 575393 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3210. Min Act: -0.0001

Data Index: 436043 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3251. Min Act: -0.0001

Data Index: 263349 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3624. Min Act: -0.0001

Data Index: 818582 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3964. Min Act: -0.0001

Data Index: 176935 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3450. Min Act: -0.0001

Data Index: 63133 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2312. Min Act: -0.0001

Data Index: 1090416 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2116. Min Act: -0.0001

Data Index: 1125567 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.3290. Min Act: -0.0001

Data Index: 46929 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.1692. Min Act: -0.0001

Data Index: 1076124 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.1889. Min Act: -0.0001

Data Index: 1429408 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.1993. Min Act: -0.0001

Data Index: 986034 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2269. Min Act: -0.0001

Data Index: 1289539 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2262. Min Act: -0.0001

Data Index: 975341 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.1760. Min Act: -0.0001

Data Index: 1018159 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.7106. Min Range: -1.7106

Max Act: 1.2096. Min Act: -0.0001

Data Index: 700138 (C4 (Web Text))

Max Activating Token Index: 480