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

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

Neuron 1510 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4888. Min Act: -0.0000

Data Index: 888956 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4870. Min Act: 0.0000

Data Index: 768935 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4706. Min Act: 0.0000

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4320. Min Act: -0.0000

Data Index: 827100 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1027078 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1197163 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3817. Min Act: -0.0000

Data Index: 683985 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3900. Min Act: -0.0000

Data Index: 508680 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3592. Min Act: -0.0000

Data Index: 264325 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3681. Min Act: -0.0000

Data Index: 80422 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3423. Min Act: -0.0000

Data Index: 971019 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1298595 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1358438 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3273. Min Act: -0.0000

Data Index: 189958 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3280. Min Act: -0.0000

Data Index: 16863 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.3345. Min Act: -0.0000

Data Index: 402917 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2908. Min Act: -0.0000

Data Index: 808910 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2940. Min Act: -0.0000

Data Index: 101476 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.4888. Min Range: -0.4888

Max Act: 0.2993. Min Act: 0.0000

Data Index: 900226 (C4 (Web Text))

Max Activating Token Index: 473