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

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

Neuron 1561 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: 3.3213. Min Range: -3.3213

Max Act: 3.3213. Min Act: -0.0000

Data Index: 1175596 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 3.3213. Min Range: -3.3213

Max Act: 2.8336. Min Act: -0.0000

Data Index: 1212883 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.3213. Min Range: -3.3213

Max Act: 2.8189. Min Act: -0.0000

Data Index: 341734 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.3213. Min Range: -3.3213

Max Act: 2.4665. Min Act: -0.0000

Data Index: 1169571 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.3213. Min Range: -3.3213

Max Act: 2.3120. Min Act: -0.0000

Data Index: 1282525 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 3.3213. Min Range: -3.3213

Max Act: 2.2564. Min Act: -0.0000

Data Index: 208437 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 3.3213. Min Range: -3.3213

Max Act: 2.1411. Min Act: -0.0000

Data Index: 877565 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 3.3213. Min Range: -3.3213

Max Act: 2.0976. Min Act: -0.0000

Data Index: 1031874 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.9374. Min Act: -0.0000

Data Index: 201843 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.8786. Min Act: -0.0000

Data Index: 497338 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.8535. Min Act: -0.0000

Data Index: 511940 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.7315. Min Act: -0.0000

Data Index: 417700 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.7554. Min Act: -0.0000

Data Index: 452240 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.7373. Min Act: -0.0000

Data Index: 299206 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.5948. Min Act: -0.0000

Data Index: 532263 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.6626. Min Act: -0.0000

Data Index: 1290999 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.5721. Min Act: -0.0000

Data Index: 839218 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.5147. Min Act: -0.0000

Data Index: 301433 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.4070. Min Act: -0.0000

Data Index: 132622 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 3.3213. Min Range: -3.3213

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1013775 (C4 (Web Text))

Max Activating Token Index: 933