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

Dataset: The Pile

Neuron 4656 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0939. Min Range: -1.0939

Max Act: 1.0939. Min Act: -0.0000

Data Index: 114169 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1151471 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1602325 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1631013 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1398005 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6042. Min Act: -0.0000

Data Index: 147397 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1028468 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1225242 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.6463. Min Act: -0.0000

Data Index: 775965 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1312191 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1580639 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5341. Min Act: -0.0000

Data Index: 520922 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5372. Min Act: -0.0000

Data Index: 316281 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1789385 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5043. Min Act: -0.0000

Data Index: 890453 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5613. Min Act: -0.0000

Data Index: 641441 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1800405 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1804950 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1926151 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.0939. Min Range: -1.0939

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1716638 (The Pile)

Max Activating Token Index: 864