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

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

Neuron 4753 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3958. Min Act: -0.0000

Data Index: 583208 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1290 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3559. Min Act: -0.0000

Data Index: 37055 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1259557 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1615743 (Python Code)

Max Activating Token Index: 632

Text #5

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3278. Min Act: -0.0000

Data Index: 404316 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3384. Min Act: -0.0000

Data Index: 1410673 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1401787 (Python Code)

Max Activating Token Index: 227

Text #8

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3414. Min Act: -0.0000

Data Index: 179828 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1317138 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3080. Min Act: -0.0000

Data Index: 928405 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3248. Min Act: -0.0000

Data Index: 1123868 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1457313 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3108. Min Act: -0.0000

Data Index: 16896 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3105. Min Act: -0.0000

Data Index: 191444 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3049. Min Act: -0.0000

Data Index: 998313 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3108. Min Act: -0.0000

Data Index: 759571 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3085. Min Act: -0.0000

Data Index: 409204 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1228009 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2957. Min Act: -0.0000

Data Index: 42481 (C4 (Web Text))

Max Activating Token Index: 35