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

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

Neuron 3332 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.4224. Min Act: -0.0000

Data Index: 778364 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3776. Min Act: 0.0000

Data Index: 1363184 (Python Code)

Max Activating Token Index: 85

Text #2

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1471198 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1550577 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3346. Min Act: -0.0000

Data Index: 754769 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1466477 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1396149 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1450053 (Python Code)

Max Activating Token Index: 550

Text #8

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1463860 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3141. Min Act: -0.0000

Data Index: 37941 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1074485 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1461105 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1525082 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3139. Min Act: -0.0000

Data Index: 21529 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1540162 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1377082 (Python Code)

Max Activating Token Index: 875

Text #16

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3008. Min Act: 0.0000

Data Index: 1085549 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1394683 (Python Code)

Max Activating Token Index: 975

Text #18

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1632666 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3072. Min Act: -0.0000

Data Index: 652713 (C4 (Web Text))

Max Activating Token Index: 183