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

Dataset: The Pile

Neuron 1701 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.9935. Min Act: -0.0000

Data Index: 118644 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.6763. Min Act: -0.0000

Data Index: 927939 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.1352. Min Act: -0.0000

Data Index: 1377957 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.4788. Min Act: -0.0000

Data Index: 1928666 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.4444. Min Act: -0.0000

Data Index: 442453 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.2618. Min Act: -0.0000

Data Index: 1249393 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.5080. Min Act: -0.0000

Data Index: 975998 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.4340. Min Act: -0.0000

Data Index: 373299 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.4061. Min Act: -0.0000

Data Index: 944527 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.3688. Min Act: -0.0000

Data Index: 937816 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.3691. Min Act: -0.0000

Data Index: 424310 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.3556. Min Act: -0.0000

Data Index: 919259 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.2973. Min Act: -0.0000

Data Index: 716121 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.3292. Min Act: -0.0000

Data Index: 1417490 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.3440. Min Act: -0.0000

Data Index: 1189532 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.3106. Min Act: -0.0000

Data Index: 116115 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.2127. Min Act: -0.0000

Data Index: 1971061 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.2361. Min Act: -0.0000

Data Index: 1742529 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.1769. Min Act: -0.0000

Data Index: 35797 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 5.9935. Min Range: -5.9935

Max Act: 5.1186. Min Act: -0.0000

Data Index: 545335 (The Pile)

Max Activating Token Index: 640