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

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

Neuron 4624 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.9020. Min Act: -0.0001

Data Index: 133262 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.5874. Min Act: -0.0001

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.5068. Min Act: -0.0000

Data Index: 434973 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.4975. Min Act: -0.0001

Data Index: 149121 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3810. Min Act: -0.0001

Data Index: 246952 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3197. Min Act: -0.0001

Data Index: 905054 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3829. Min Act: -0.0001

Data Index: 1086573 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.2757. Min Act: -0.0001

Data Index: 577323 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.4588. Min Act: -0.0001

Data Index: 1095658 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3500. Min Act: -0.0001

Data Index: 247871 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.2996. Min Act: -0.0001

Data Index: 359164 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3424. Min Act: -0.0001

Data Index: 1236421 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3574. Min Act: -0.0001

Data Index: 374214 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3051. Min Act: -0.0001

Data Index: 582954 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.2182. Min Act: -0.0001

Data Index: 739244 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3410. Min Act: -0.0001

Data Index: 93620 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1187406 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.3440. Min Act: -0.0001

Data Index: 754368 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.2264. Min Act: -0.0001

Data Index: 116684 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 1.9020. Min Range: -1.9020

Max Act: 1.2447. Min Act: -0.0001

Data Index: 358646 (C4 (Web Text))

Max Activating Token Index: 372