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

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

Neuron 3889 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1112272 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5964. Min Act: -0.0000

Data Index: 702679 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5448. Min Act: -0.0000

Data Index: 674983 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1328468 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4206. Min Act: -0.0000

Data Index: 224194 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4365. Min Act: -0.0000

Data Index: 961195 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3886. Min Act: -0.0000

Data Index: 319323 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1349047 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4122. Min Act: -0.0000

Data Index: 339402 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3978. Min Act: -0.0000

Data Index: 242077 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.4139. Min Act: -0.0000

Data Index: 463991 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3885. Min Act: -0.0000

Data Index: 9796 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3703. Min Act: -0.0000

Data Index: 839801 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3939. Min Act: -0.0000

Data Index: 157606 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3673. Min Act: -0.0000

Data Index: 92888 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3370. Min Act: -0.0000

Data Index: 984324 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3354. Min Act: 0.0000

Data Index: 156263 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3450. Min Act: -0.0000

Data Index: 611331 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1168593 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.5983. Min Range: -0.5983

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1150749 (C4 (Web Text))

Max Activating Token Index: 416