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

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

Neuron 2108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: -0.0001

Data Index: 330560 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1163. Min Act: -0.0001

Data Index: 815267 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1265. Min Act: -0.0001

Data Index: 506048 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1254. Min Act: -0.0001

Data Index: 127379 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1331095 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1324656 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1163. Min Act: -0.0001

Data Index: 597419 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1247. Min Act: -0.0001

Data Index: 47125 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1074771 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1173. Min Act: -0.0001

Data Index: 917852 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1133. Min Act: -0.0001

Data Index: 741342 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0914. Min Act: -0.0001

Data Index: 797727 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0988. Min Act: -0.0001

Data Index: 605043 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1007057 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1041. Min Act: -0.0001

Data Index: 852740 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1096290 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1023. Min Act: -0.0001

Data Index: 668985 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1038. Min Act: -0.0001

Data Index: 67073 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1273018 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0893. Min Act: -0.0001

Data Index: 686128 (C4 (Web Text))

Max Activating Token Index: 554