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

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

Neuron 546 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8295. Min Range: -5.8295

Max Act: 5.8295. Min Act: -0.0000

Data Index: 367890 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 5.8295. Min Range: -5.8295

Max Act: 5.3892. Min Act: -0.0000

Data Index: 1066289 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 5.8295. Min Range: -5.8295

Max Act: 5.6374. Min Act: -0.0000

Data Index: 898213 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 5.8295. Min Range: -5.8295

Max Act: 5.0476. Min Act: -0.0000

Data Index: 395618 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.8588. Min Act: -0.0000

Data Index: 1358013 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.7433. Min Act: -0.0000

Data Index: 1081278 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.5353. Min Act: -0.0000

Data Index: 1254081 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.3912. Min Act: -0.0000

Data Index: 1022549 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.3482. Min Act: -0.0000

Data Index: 311488 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.6564. Min Act: -0.0000

Data Index: 873453 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.2884. Min Act: -0.0000

Data Index: 1158436 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.4491. Min Act: -0.0000

Data Index: 1209846 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.5695. Min Act: -0.0000

Data Index: 1033170 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.5760. Min Act: -0.0000

Data Index: 1326034 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.4057. Min Act: -0.0000

Data Index: 98690 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.3761. Min Act: -0.0000

Data Index: 388639 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.3333. Min Act: -0.0000

Data Index: 1185095 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 5.8295. Min Range: -5.8295

Max Act: 3.8927. Min Act: -0.0000

Data Index: 1162471 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.2211. Min Act: -0.0000

Data Index: 863435 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 5.8295. Min Range: -5.8295

Max Act: 4.2154. Min Act: -0.0000

Data Index: 427346 (C4 (Web Text))

Max Activating Token Index: 456