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

Dataset: The Pile

Neuron 3983 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: 0.5101. Min Range: -0.5101

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1504832 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4420. Min Act: -0.0000

Data Index: 23197 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1145849 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3664. Min Act: -0.0000

Data Index: 555353 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3455. Min Act: -0.0000

Data Index: 708170 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1435121 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1880254 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3475. Min Act: -0.0000

Data Index: 420577 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3691. Min Act: -0.0000

Data Index: 694198 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1970286 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1835913 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3551. Min Act: -0.0000

Data Index: 413100 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3796. Min Act: -0.0000

Data Index: 19488 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1857258 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3783. Min Act: -0.0000

Data Index: 225994 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1651830 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3579. Min Act: -0.0000

Data Index: 637258 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1442670 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1321108 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 0.5101. Min Range: -0.5101

Max Act: 0.3321. Min Act: -0.0000

Data Index: 923335 (The Pile)

Max Activating Token Index: 185