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

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

Neuron 38 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3650. Min Act: -0.0000

Data Index: 623136 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3110. Min Act: -0.0000

Data Index: 650576 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3320. Min Act: -0.0000

Data Index: 745056 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1191362 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1328577 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3355. Min Act: -0.0000

Data Index: 755414 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1636412 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3076. Min Act: -0.0000

Data Index: 576879 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1002754 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3131. Min Act: -0.0000

Data Index: 73766 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3003. Min Act: -0.0000

Data Index: 302421 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3083. Min Act: -0.0000

Data Index: 720631 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2968. Min Act: -0.0000

Data Index: 649084 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3049. Min Act: -0.0000

Data Index: 398626 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3039. Min Act: -0.0000

Data Index: 82935 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2964. Min Act: -0.0000

Data Index: 930138 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2867. Min Act: -0.0000

Data Index: 823895 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2963. Min Act: -0.0000

Data Index: 456325 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.2965. Min Act: -0.0000

Data Index: 916579 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.3650. Min Range: -0.3650

Max Act: 0.3054. Min Act: -0.0000

Data Index: 477701 (C4 (Web Text))

Max Activating Token Index: 284