Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 929 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0929. Min Act: -0.0001

Data Index: 1558368 (Python Code)

Max Activating Token Index: 785

Text #1

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0997. Min Act: -0.0001

Data Index: 1389370 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1986. Min Act: -0.0001

Data Index: 1057787 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1475. Min Act: -0.0001

Data Index: 1142721 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1004. Min Act: -0.0001

Data Index: 1516025 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1137. Min Act: -0.0001

Data Index: 1597027 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1954. Min Act: -0.0001

Data Index: 485566 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1054. Min Act: -0.0001

Data Index: 1407404 (Python Code)

Max Activating Token Index: 969

Text #8

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1172. Min Act: -0.0001

Data Index: 496920 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0472. Min Act: -0.0001

Data Index: 521280 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9762. Min Act: -0.0001

Data Index: 1562794 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1280. Min Act: -0.0001

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0621. Min Act: -0.0001

Data Index: 1609888 (Python Code)

Max Activating Token Index: 917

Text #13

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1273. Min Act: -0.0001

Data Index: 1386377 (Python Code)

Max Activating Token Index: 207

Text #14

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1160. Min Act: -0.0001

Data Index: 1205622 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0503. Min Act: -0.0001

Data Index: 465024 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0460. Min Act: -0.0001

Data Index: 1370190 (Python Code)

Max Activating Token Index: 796

Text #17

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0615. Min Act: -0.0001

Data Index: 1581862 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1157. Min Act: -0.0001

Data Index: 876609 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9001. Min Act: -0.0001

Data Index: 1372641 (Python Code)

Max Activating Token Index: 300