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

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

Neuron 1725 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0987. Min Range: -2.0987

Max Act: 2.0987. Min Act: -0.0000

Data Index: 288915 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.7741. Min Act: -0.0000

Data Index: 1106111 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.6780. Min Act: -0.0000

Data Index: 873398 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.5535. Min Act: -0.0000

Data Index: 299232 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.5483. Min Act: -0.0000

Data Index: 900573 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.5475. Min Act: -0.0000

Data Index: 1266304 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.4196. Min Act: -0.0000

Data Index: 718195 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.4916. Min Act: -0.0000

Data Index: 667825 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.4325. Min Act: -0.0000

Data Index: 649997 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.4221. Min Act: -0.0000

Data Index: 588000 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.3237. Min Act: 0.0000

Data Index: 1276815 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.4088. Min Act: -0.0000

Data Index: 368719 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.4518. Min Act: -0.0000

Data Index: 605090 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.2893. Min Act: -0.0000

Data Index: 766747 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.3677. Min Act: -0.0000

Data Index: 360993 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.3492. Min Act: -0.0000

Data Index: 392359 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.3613. Min Act: -0.0000

Data Index: 698512 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.3498. Min Act: -0.0000

Data Index: 1285678 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.3113. Min Act: -0.0000

Data Index: 822850 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 2.0987. Min Range: -2.0987

Max Act: 1.4536. Min Act: -0.0000

Data Index: 124523 (C4 (Web Text))

Max Activating Token Index: 670