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

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

Neuron 3363 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.7934. Min Act: -0.0001

Data Index: 661539 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.4597. Min Act: -0.0001

Data Index: 661028 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.3145. Min Act: -0.0001

Data Index: 1172358 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.2891. Min Act: -0.0001

Data Index: 684283 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.1205. Min Act: -0.0001

Data Index: 1172947 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.8275. Min Act: -0.0001

Data Index: 140648 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.9504. Min Act: -0.0001

Data Index: 386200 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.1935. Min Act: -0.0001

Data Index: 67980 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.9245. Min Act: -0.0001

Data Index: 536182 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.0415. Min Act: -0.0001

Data Index: 9297 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.0479. Min Act: -0.0001

Data Index: 962686 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.8978. Min Act: -0.0001

Data Index: 87077 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 3.7934. Min Range: -3.7934

Max Act: 3.0137. Min Act: -0.0001

Data Index: 225622 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.7514. Min Act: -0.0001

Data Index: 917059 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.6364. Min Act: -0.0001

Data Index: 628070 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.8203. Min Act: -0.0001

Data Index: 982849 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.9643. Min Act: -0.0001

Data Index: 1228999 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.8281. Min Act: -0.0001

Data Index: 615856 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.8127. Min Act: -0.0001

Data Index: 595760 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 3.7934. Min Range: -3.7934

Max Act: 2.8071. Min Act: -0.0001

Data Index: 13393 (C4 (Web Text))

Max Activating Token Index: 278