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

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

Neuron 1812 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1362701 (Python Code)

Max Activating Token Index: 1009

Text #1

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7289. Min Act: -0.0001

Data Index: 1457043 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7719. Min Act: -0.0001

Data Index: 1302417 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7196. Min Act: -0.0001

Data Index: 306706 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6951. Min Act: -0.0001

Data Index: 60581 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7573. Min Act: -0.0001

Data Index: 1380378 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6942. Min Act: -0.0001

Data Index: 1242958 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6492. Min Act: -0.0001

Data Index: 1534517 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6487. Min Act: -0.0001

Data Index: 756226 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6599. Min Act: -0.0001

Data Index: 909141 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6153. Min Act: -0.0001

Data Index: 338790 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6132. Min Act: -0.0001

Data Index: 438336 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6510. Min Act: -0.0001

Data Index: 1561846 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5950. Min Act: -0.0001

Data Index: 783393 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5908. Min Act: -0.0001

Data Index: 797665 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6068. Min Act: -0.0001

Data Index: 370979 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5694. Min Act: -0.0001

Data Index: 360727 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6044. Min Act: -0.0001

Data Index: 430310 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6223. Min Act: -0.0001

Data Index: 1272474 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6037. Min Act: -0.0001

Data Index: 1271293 (C4 (Web Text))

Max Activating Token Index: 145