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

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

Neuron 3853 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8956. Min Act: -0.0001

Data Index: 841246 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7843. Min Act: -0.0001

Data Index: 823760 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8068. Min Act: -0.0001

Data Index: 1110542 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1274915 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1026958 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1092692 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7796. Min Act: -0.0002

Data Index: 541722 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7778. Min Act: -0.0002

Data Index: 305184 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7973. Min Act: -0.0002

Data Index: 731383 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7629. Min Act: -0.0002

Data Index: 674712 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7866. Min Act: -0.0001

Data Index: 993273 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7549. Min Act: -0.0002

Data Index: 932434 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7945. Min Act: -0.0002

Data Index: 1216371 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7190. Min Act: -0.0001

Data Index: 805396 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7290. Min Act: -0.0001

Data Index: 206505 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7452. Min Act: -0.0001

Data Index: 188649 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7277. Min Act: -0.0001

Data Index: 1163846 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7397. Min Act: -0.0002

Data Index: 377935 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6929. Min Act: -0.0001

Data Index: 336378 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1531990 (Python Code)

Max Activating Token Index: 39