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

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

Neuron 157 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8452. Min Range: -4.8452

Max Act: 4.8452. Min Act: -0.0000

Data Index: 473292 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 4.8452. Min Range: -4.8452

Max Act: 4.0719. Min Act: -0.0000

Data Index: 208710 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 4.8452. Min Range: -4.8452

Max Act: 4.2123. Min Act: 0.0000

Data Index: 109817 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.8338. Min Act: -0.0000

Data Index: 409273 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.8305. Min Act: -0.0000

Data Index: 366394 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.5796. Min Act: -0.0000

Data Index: 105510 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.7208. Min Act: -0.0000

Data Index: 790026 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.5247. Min Act: 0.0000

Data Index: 205439 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.6445. Min Act: -0.0000

Data Index: 699222 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.9618. Min Act: -0.0000

Data Index: 552323 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.4279. Min Act: -0.0000

Data Index: 389399 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.6105. Min Act: -0.0000

Data Index: 292221 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.5707. Min Act: -0.0000

Data Index: 1172362 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.6597. Min Act: -0.0000

Data Index: 108989 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.3730. Min Act: -0.0000

Data Index: 647416 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.2240. Min Act: -0.0000

Data Index: 699566 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.6677. Min Act: -0.0000

Data Index: 339736 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.2651. Min Act: -0.0000

Data Index: 1274364 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.1032. Min Act: -0.0000

Data Index: 1255815 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 4.8452. Min Range: -4.8452

Max Act: 3.1924. Min Act: -0.0000

Data Index: 761557 (C4 (Web Text))

Max Activating Token Index: 346