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

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

Neuron 2212 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6020. Min Range: -4.6020

Max Act: 4.6020. Min Act: -0.0000

Data Index: 15569 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 4.6020. Min Range: -4.6020

Max Act: 3.3277. Min Act: -0.0000

Data Index: 492221 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 4.6020. Min Range: -4.6020

Max Act: 3.4137. Min Act: -0.0000

Data Index: 1058903 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 4.6020. Min Range: -4.6020

Max Act: 3.0313. Min Act: -0.0000

Data Index: 172954 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.8185. Min Act: -0.0000

Data Index: 251379 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.8261. Min Act: -0.0000

Data Index: 1097628 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.6409. Min Act: -0.0000

Data Index: 825137 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.7347. Min Act: -0.0000

Data Index: 866019 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.7537. Min Act: -0.0000

Data Index: 227129 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.5877. Min Act: -0.0000

Data Index: 45201 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.3708. Min Act: -0.0000

Data Index: 384235 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.4398. Min Act: -0.0000

Data Index: 454830 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.2795. Min Act: -0.0000

Data Index: 593609 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.2280. Min Act: -0.0000

Data Index: 473124 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.0838. Min Act: -0.0000

Data Index: 533956 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.0640. Min Act: -0.0000

Data Index: 253607 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.1567. Min Act: -0.0000

Data Index: 1176656 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.1274. Min Act: -0.0000

Data Index: 667465 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 4.6020. Min Range: -4.6020

Max Act: 1.8920. Min Act: -0.0000

Data Index: 414348 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 4.6020. Min Range: -4.6020

Max Act: 2.0541. Min Act: -0.0000

Data Index: 1182260 (C4 (Web Text))

Max Activating Token Index: 237