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

Dataset: The Pile

Neuron 3324 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: 0.4935. Min Range: -0.4935

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1659463 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1962101 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1962772 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4935. Min Act: -0.0000

Data Index: 33006 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4866. Min Act: -0.0000

Data Index: 175204 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1744683 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1566809 (The Pile)

Max Activating Token Index: 588

Text #7

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4104. Min Act: -0.0000

Data Index: 372342 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1099272 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1091594 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4421. Min Act: -0.0000

Data Index: 47741 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4398. Min Act: -0.0000

Data Index: 908339 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4070. Min Act: -0.0000

Data Index: 465215 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4069. Min Act: -0.0000

Data Index: 665790 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3777. Min Act: -0.0000

Data Index: 756843 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4050. Min Act: -0.0000

Data Index: 957943 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1808842 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1150823 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3674. Min Act: -0.0000

Data Index: 631775 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1599582 (The Pile)

Max Activating Token Index: 476