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

Dataset: The Pile

Neuron 4827 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: 0.6640. Min Range: -0.6640

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1290205 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5076. Min Act: -0.0000

Data Index: 611173 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4960. Min Act: -0.0000

Data Index: 757615 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4977. Min Act: -0.0000

Data Index: 808223 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4558. Min Act: -0.0000

Data Index: 351817 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1629692 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1964579 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1423747 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1849792 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3903. Min Act: -0.0000

Data Index: 233944 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1106592 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1752824 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3269. Min Act: -0.0000

Data Index: 578089 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1870078 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1932779 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1535471 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1010746 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.2577. Min Act: -0.0000

Data Index: 230680 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1868064 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1922503 (The Pile)

Max Activating Token Index: 203