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

Dataset: The Pile

Neuron 2814 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.1288. Min Act: -0.0000

Data Index: 605516 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0008. Min Act: -0.0000

Data Index: 535635 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1279205 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8252. Min Act: -0.0000

Data Index: 884557 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1463754 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8011. Min Act: -0.0000

Data Index: 148938 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1756543 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7532. Min Act: -0.0000

Data Index: 692228 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7578. Min Act: -0.0000

Data Index: 560833 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1518717 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1569515 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1782122 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1401069 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.6904. Min Act: -0.0000

Data Index: 457360 (The Pile)

Max Activating Token Index: 899

Text #14

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1255028 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1458270 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1561104 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1997581 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1844219 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1679242 (The Pile)

Max Activating Token Index: 730