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

Dataset: The Pile

Neuron 2742 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3907. Min Act: -0.0000

Data Index: 716817 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1931136 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1751900 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3932. Min Act: -0.0000

Data Index: 419445 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1068522 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4081. Min Act: -0.0000

Data Index: 186980 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1364000 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1752684 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4032. Min Act: -0.0000

Data Index: 257501 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3145. Min Act: -0.0000

Data Index: 643272 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3224. Min Act: -0.0000

Data Index: 470422 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1598494 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1299542 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2902. Min Act: -0.0000

Data Index: 968527 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2600. Min Act: -0.0000

Data Index: 182571 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3024. Min Act: -0.0000

Data Index: 473563 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1729838 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2805. Min Act: -0.0000

Data Index: 556144 (The Pile)

Max Activating Token Index: 884

Text #18

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2797. Min Act: -0.0000

Data Index: 192812 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1935316 (The Pile)

Max Activating Token Index: 66