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

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

Neuron 302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1258535 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5463. Min Act: -0.0000

Data Index: 73357 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5810. Min Act: -0.0001

Data Index: 473922 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1108115 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5227. Min Act: -0.0001

Data Index: 670312 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1171752 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1128122 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1272093 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4575. Min Act: -0.0000

Data Index: 527371 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4276. Min Act: -0.0001

Data Index: 1041916 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4378. Min Act: -0.0000

Data Index: 113700 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4255. Min Act: -0.0001

Data Index: 922103 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1267903 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1110879 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4386. Min Act: -0.0000

Data Index: 436647 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4380. Min Act: -0.0000

Data Index: 434442 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4053. Min Act: -0.0000

Data Index: 823315 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1232941 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4457. Min Act: -0.0000

Data Index: 156224 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.5835. Min Range: -0.5835

Max Act: 0.4139. Min Act: -0.0000

Data Index: 832136 (C4 (Web Text))

Max Activating Token Index: 652