Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.5172. Min Act: -0.0000

Data Index: 1462613 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1433. Min Act: -0.0000

Data Index: 1571959 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.3739. Min Act: -0.0000

Data Index: 402888 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.4326. Min Act: -0.0000

Data Index: 182240 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.3192. Min Act: -0.0000

Data Index: 1154938 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.1963. Min Act: -0.0000

Data Index: 430331 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 3.5172. Min Range: -3.5172

Max Act: 3.1185. Min Act: -0.0000

Data Index: 1500670 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.5878. Min Act: -0.0000

Data Index: 141026 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.5617. Min Act: -0.0000

Data Index: 1223135 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.4350. Min Act: -0.0000

Data Index: 1248235 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.2754. Min Act: -0.0000

Data Index: 885749 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.3630. Min Act: -0.0000

Data Index: 1643456 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.2597. Min Act: -0.0000

Data Index: 1037327 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.5553. Min Act: -0.0000

Data Index: 41549 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 3.5172. Min Range: -3.5172

Max Act: 2.0391. Min Act: -0.0000

Data Index: 1423211 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 3.5172. Min Range: -3.5172

Max Act: 1.4955. Min Act: -0.0000

Data Index: 1308335 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 3.5172. Min Range: -3.5172

Max Act: 1.7642. Min Act: -0.0000

Data Index: 1018551 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 3.5172. Min Range: -3.5172

Max Act: 1.6215. Min Act: -0.0000

Data Index: 1726227 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 3.5172. Min Range: -3.5172

Max Act: 1.6897. Min Act: -0.0000

Data Index: 747907 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 3.5172. Min Range: -3.5172

Max Act: 1.8284. Min Act: -0.0000

Data Index: 519592 (The Pile)

Max Activating Token Index: 885