Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3243 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.8193. Min Act: -0.0000

Data Index: 1540024 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7114. Min Act: -0.0000

Data Index: 1425619 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.6509. Min Act: -0.0000

Data Index: 376141 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.8207. Min Act: -0.0000

Data Index: 1311958 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1497931 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.3128. Min Act: -0.0000

Data Index: 1264551 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1117734 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1486766 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.2533. Min Act: -0.0000

Data Index: 963211 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1332363 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1529245 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.5762. Min Act: -0.0000

Data Index: 297654 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.1072. Min Act: -0.0000

Data Index: 481537 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1335229 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1782707 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.2862. Min Act: -0.0000

Data Index: 1272037 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.1250. Min Act: -0.0000

Data Index: 135474 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1284161 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.2363. Min Act: -0.0000

Data Index: 784772 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1077794 (The Pile)

Max Activating Token Index: 745