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

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

Neuron 4910 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: 4.4801. Min Range: -4.4801

Max Act: 4.4801. Min Act: -0.0000

Data Index: 1506338 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.9343. Min Act: -0.0000

Data Index: 1366646 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.6964. Min Act: -0.0000

Data Index: 1366719 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.5722. Min Act: -0.0000

Data Index: 1463363 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.3434. Min Act: -0.0000

Data Index: 1391355 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.3402. Min Act: -0.0000

Data Index: 1390397 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.3062. Min Act: -0.0000

Data Index: 1652990 (Python Code)

Max Activating Token Index: 220

Text #7

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.4052. Min Act: -0.0000

Data Index: 1427858 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 4.4801. Min Range: -4.4801

Max Act: 3.0778. Min Act: -0.0000

Data Index: 1629571 (Python Code)

Max Activating Token Index: 471

Text #9

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.7790. Min Act: -0.0000

Data Index: 1422457 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.7471. Min Act: -0.0000

Data Index: 1439147 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.6790. Min Act: -0.0000

Data Index: 1558001 (Python Code)

Max Activating Token Index: 872

Text #12

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.5732. Min Act: -0.0000

Data Index: 1439265 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.3573. Min Act: -0.0000

Data Index: 1428913 (Python Code)

Max Activating Token Index: 420

Text #14

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.6564. Min Act: -0.0000

Data Index: 1631964 (Python Code)

Max Activating Token Index: 260

Text #15

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.4974. Min Act: -0.0000

Data Index: 1524602 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.6197. Min Act: -0.0000

Data Index: 1378175 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.4465. Min Act: -0.0000

Data Index: 1629217 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.4140. Min Act: -0.0000

Data Index: 1652260 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 4.4801. Min Range: -4.4801

Max Act: 2.4038. Min Act: -0.0000

Data Index: 1568033 (Python Code)

Max Activating Token Index: 254