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

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

Neuron 1881 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: 7.4831. Min Range: -7.4831

Max Act: 7.4831. Min Act: -0.0000

Data Index: 862642 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 7.4831. Min Range: -7.4831

Max Act: 6.4786. Min Act: -0.0000

Data Index: 1220225 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 7.4831. Min Range: -7.4831

Max Act: 6.2503. Min Act: -0.0000

Data Index: 902152 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 7.4831. Min Range: -7.4831

Max Act: 6.4290. Min Act: -0.0000

Data Index: 810607 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 7.4831. Min Range: -7.4831

Max Act: 6.5298. Min Act: -0.0000

Data Index: 792392 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 7.4831. Min Range: -7.4831

Max Act: 6.2760. Min Act: -0.0000

Data Index: 733977 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 7.4831. Min Range: -7.4831

Max Act: 6.4099. Min Act: -0.0000

Data Index: 450806 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 7.4831. Min Range: -7.4831

Max Act: 6.2405. Min Act: -0.0000

Data Index: 1157052 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 7.4831. Min Range: -7.4831

Max Act: 5.0879. Min Act: -0.0000

Data Index: 601546 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 7.4831. Min Range: -7.4831

Max Act: 5.6386. Min Act: -0.0000

Data Index: 667889 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 7.4831. Min Range: -7.4831

Max Act: 4.4182. Min Act: -0.0000

Data Index: 59493 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 7.4831. Min Range: -7.4831

Max Act: 5.2042. Min Act: -0.0000

Data Index: 148336 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 7.4831. Min Range: -7.4831

Max Act: 5.9567. Min Act: -0.0000

Data Index: 1153328 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 7.4831. Min Range: -7.4831

Max Act: 5.6366. Min Act: -0.0000

Data Index: 1071556 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 7.4831. Min Range: -7.4831

Max Act: 5.3947. Min Act: -0.0000

Data Index: 957917 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 7.4831. Min Range: -7.4831

Max Act: 4.9943. Min Act: -0.0000

Data Index: 890773 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 7.4831. Min Range: -7.4831

Max Act: 5.2608. Min Act: -0.0000

Data Index: 78413 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 7.4831. Min Range: -7.4831

Max Act: 4.2395. Min Act: -0.0000

Data Index: 470600 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 7.4831. Min Range: -7.4831

Max Act: 4.7740. Min Act: -0.0000

Data Index: 202403 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 7.4831. Min Range: -7.4831

Max Act: 4.2936. Min Act: -0.0000

Data Index: 1299897 (C4 (Web Text))

Max Activating Token Index: 274