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

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

Neuron 518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1077764 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.3125. Min Act: -0.0000

Data Index: 702155 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1548757 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2843. Min Act: -0.0000

Data Index: 570963 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2470. Min Act: -0.0000

Data Index: 255601 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1494647 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.1944. Min Act: -0.0000

Data Index: 614521 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2106. Min Act: -0.0000

Data Index: 409928 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1590859 (Python Code)

Max Activating Token Index: 590

Text #9

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1207884 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1377618 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2240. Min Act: -0.0000

Data Index: 742899 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1573462 (Python Code)

Max Activating Token Index: 57

Text #13

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1140914 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2293. Min Act: -0.0000

Data Index: 921215 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2296. Min Act: -0.0000

Data Index: 220793 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2215. Min Act: -0.0000

Data Index: 26669 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1357989 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1543254 (Python Code)

Max Activating Token Index: 239

Text #19

Max Range: 0.3414. Min Range: -0.3414

Max Act: 0.2122. Min Act: -0.0000

Data Index: 926957 (C4 (Web Text))

Max Activating Token Index: 786