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

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

Neuron 3674 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0001

Data Index: 501540 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2518. Min Act: -0.0001

Data Index: 651227 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2656. Min Act: -0.0001

Data Index: 445666 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1301011 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1952. Min Act: -0.0001

Data Index: 856662 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1235302 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2108. Min Act: -0.0001

Data Index: 38723 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2363. Min Act: -0.0001

Data Index: 1155822 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2063. Min Act: -0.0001

Data Index: 545387 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2333. Min Act: -0.0001

Data Index: 77824 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2120. Min Act: -0.0001

Data Index: 17564 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1251684 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1787. Min Act: -0.0001

Data Index: 115127 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2083. Min Act: -0.0001

Data Index: 177218 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2457. Min Act: -0.0001

Data Index: 152382 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2121. Min Act: -0.0001

Data Index: 1077897 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1044378 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2170. Min Act: -0.0001

Data Index: 347043 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1933. Min Act: -0.0001

Data Index: 328005 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2152. Min Act: -0.0001

Data Index: 999036 (C4 (Web Text))

Max Activating Token Index: 517