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

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

Neuron 2459 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: 4.1370. Min Range: -4.1370

Max Act: 4.1370. Min Act: -0.0000

Data Index: 145023 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 4.1370. Min Range: -4.1370

Max Act: 3.8718. Min Act: -0.0000

Data Index: 346257 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 4.1370. Min Range: -4.1370

Max Act: 3.7324. Min Act: -0.0000

Data Index: 518369 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 4.1370. Min Range: -4.1370

Max Act: 3.4911. Min Act: -0.0000

Data Index: 759999 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.7844. Min Act: -0.0000

Data Index: 57208 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 4.1370. Min Range: -4.1370

Max Act: 3.0083. Min Act: -0.0000

Data Index: 31156 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.9547. Min Act: -0.0000

Data Index: 423837 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.8645. Min Act: -0.0000

Data Index: 1106087 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.9205. Min Act: -0.0000

Data Index: 527324 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.7067. Min Act: -0.0000

Data Index: 945644 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.6958. Min Act: -0.0000

Data Index: 521801 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.7514. Min Act: -0.0000

Data Index: 990149 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.7151. Min Act: -0.0000

Data Index: 305476 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.5223. Min Act: -0.0000

Data Index: 341912 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.4945. Min Act: -0.0000

Data Index: 101626 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.4780. Min Act: -0.0000

Data Index: 401282 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.4578. Min Act: -0.0000

Data Index: 381834 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.4467. Min Act: -0.0000

Data Index: 14284 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.3962. Min Act: -0.0000

Data Index: 442324 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 4.1370. Min Range: -4.1370

Max Act: 2.3805. Min Act: -0.0000

Data Index: 388671 (C4 (Web Text))

Max Activating Token Index: 770