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

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

Neuron 2261 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1080. Min Range: -2.1080

Max Act: 2.1080. Min Act: -0.0000

Data Index: 841821 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1086297 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.9441. Min Act: -0.0000

Data Index: 786090 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.9099. Min Act: -0.0000

Data Index: 972333 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.9451. Min Act: -0.0000

Data Index: 867172 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.7361. Min Act: -0.0000

Data Index: 601977 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.7930. Min Act: -0.0000

Data Index: 33798 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.8595. Min Act: -0.0000

Data Index: 966995 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.7335. Min Act: -0.0000

Data Index: 162269 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.8306. Min Act: -0.0000

Data Index: 855787 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.5640. Min Act: -0.0000

Data Index: 288017 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.6816. Min Act: -0.0000

Data Index: 1173364 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.5537. Min Act: -0.0000

Data Index: 636603 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1084257 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.4525. Min Act: -0.0000

Data Index: 743352 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.5383. Min Act: -0.0000

Data Index: 1234647 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.4484. Min Act: -0.0000

Data Index: 35850 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.4245. Min Act: -0.0000

Data Index: 914183 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.4945. Min Act: -0.0000

Data Index: 708674 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 2.1080. Min Range: -2.1080

Max Act: 1.4000. Min Act: -0.0000

Data Index: 1090188 (C4 (Web Text))

Max Activating Token Index: 1016