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

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

Neuron 3509 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: 1.4131. Min Range: -1.4131

Max Act: 1.3865. Min Act: -0.0000

Data Index: 909193 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.4131. Min Act: -0.0000

Data Index: 688633 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.4034. Min Act: -0.0000

Data Index: 613120 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.2578. Min Act: -0.0000

Data Index: 391092 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1414018 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1607881 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1369239 (Python Code)

Max Activating Token Index: 757

Text #7

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1416249 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.2176. Min Act: -0.0000

Data Index: 549576 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.1506. Min Act: -0.0000

Data Index: 877128 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1654497 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0791. Min Act: -0.0000

Data Index: 755680 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0727. Min Act: -0.0000

Data Index: 767074 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1307509 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0079. Min Act: -0.0000

Data Index: 137718 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0340. Min Act: -0.0000

Data Index: 925548 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.4131. Min Range: -1.4131

Max Act: 0.9821. Min Act: -0.0000

Data Index: 1150205 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1058606 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1500086 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 1.4131. Min Range: -1.4131

Max Act: 1.0505. Min Act: -0.0000

Data Index: 551063 (C4 (Web Text))

Max Activating Token Index: 43