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

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

Neuron 169 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.3532. Min Act: -0.0001

Data Index: 679524 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.3199. Min Act: -0.0001

Data Index: 132572 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.2063. Min Act: -0.0001

Data Index: 485082 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.2074. Min Act: -0.0001

Data Index: 1252020 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0596. Min Act: -0.0001

Data Index: 936861 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.2192. Min Act: -0.0001

Data Index: 264717 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.1123. Min Act: -0.0001

Data Index: 1354951 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.1397. Min Act: -0.0001

Data Index: 562014 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.1367. Min Act: -0.0001

Data Index: 593041 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.1292. Min Act: -0.0001

Data Index: 920242 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0674. Min Act: -0.0001

Data Index: 875621 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0904. Min Act: -0.0001

Data Index: 168290 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0894. Min Act: -0.0001

Data Index: 1186631 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0474. Min Act: -0.0001

Data Index: 1040097 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0124. Min Act: -0.0001

Data Index: 180689 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0340. Min Act: -0.0001

Data Index: 965383 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.3532. Min Range: -1.3532

Max Act: 0.9978. Min Act: -0.0001

Data Index: 768689 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0835. Min Act: -0.0001

Data Index: 565231 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.0613. Min Act: -0.0001

Data Index: 475754 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 1.3532. Min Range: -1.3532

Max Act: 1.1058. Min Act: -0.0001

Data Index: 728331 (C4 (Web Text))

Max Activating Token Index: 597