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

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

Neuron 3989 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1388650 (Python Code)

Max Activating Token Index: 321

Text #1

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6900. Min Act: -0.0000

Data Index: 645985 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5661. Min Act: -0.0000

Data Index: 169009 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1006283 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5231. Min Act: -0.0000

Data Index: 206691 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5631. Min Act: -0.0000

Data Index: 425863 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1237879 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1144179 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1157317 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1313108 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5109. Min Act: -0.0000

Data Index: 252219 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5028. Min Act: -0.0000

Data Index: 269513 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4983. Min Act: -0.0000

Data Index: 651088 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5091. Min Act: -0.0000

Data Index: 466328 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5178. Min Act: -0.0000

Data Index: 59963 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1437437 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4882. Min Act: -0.0000

Data Index: 351885 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4778. Min Act: -0.0000

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4989. Min Act: -0.0000

Data Index: 300340 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1612944 (Python Code)

Max Activating Token Index: 709