Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5323 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.9230. Min Act: -0.0000

Data Index: 792839 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.6525. Min Act: -0.0000

Data Index: 826098 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.5735. Min Act: -0.0000

Data Index: 821195 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.6908. Min Act: -0.0000

Data Index: 209895 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.7074. Min Act: -0.0000

Data Index: 1199757 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.7323. Min Act: -0.0000

Data Index: 249199 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.3286. Min Act: -0.0000

Data Index: 130512 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.2491. Min Act: -0.0000

Data Index: 95370 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.1120. Min Act: -0.0000

Data Index: 440828 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 3.9230. Min Range: -3.9230

Max Act: 3.0199. Min Act: -0.0000

Data Index: 182763 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.8410. Min Act: -0.0000

Data Index: 412182 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.7260. Min Act: -0.0000

Data Index: 785223 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.7933. Min Act: -0.0000

Data Index: 918814 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.4761. Min Act: -0.0000

Data Index: 983593 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.6957. Min Act: -0.0000

Data Index: 74198 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.4282. Min Act: -0.0000

Data Index: 482334 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.5383. Min Act: -0.0000

Data Index: 999448 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.4151. Min Act: -0.0000

Data Index: 993358 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.2093. Min Act: -0.0000

Data Index: 1345231 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.9230. Min Range: -3.9230

Max Act: 2.4475. Min Act: -0.0000

Data Index: 1132702 (C4 (Web Text))

Max Activating Token Index: 126