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

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

Neuron 3119 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.9107. Min Act: -0.0000

Data Index: 969541 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8520. Min Act: -0.0000

Data Index: 401805 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7610. Min Act: -0.0001

Data Index: 115481 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7857. Min Act: -0.0000

Data Index: 358453 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1121118 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7788. Min Act: -0.0001

Data Index: 436249 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8192. Min Act: -0.0000

Data Index: 871091 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8086. Min Act: -0.0000

Data Index: 118443 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7518. Min Act: -0.0000

Data Index: 643232 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8101. Min Act: -0.0001

Data Index: 385943 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8249. Min Act: -0.0000

Data Index: 70914 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7954. Min Act: -0.0000

Data Index: 891672 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1137461 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7918. Min Act: -0.0000

Data Index: 810130 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8145. Min Act: -0.0000

Data Index: 264136 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.8182. Min Act: -0.0000

Data Index: 124233 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1146279 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7848. Min Act: -0.0000

Data Index: 29643 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7753. Min Act: -0.0000

Data Index: 362892 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.9107. Min Range: -0.9107

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1046924 (C4 (Web Text))

Max Activating Token Index: 479