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

Dataset: The Pile

Neuron 3189 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: 3.2483. Min Range: -3.2483

Max Act: 3.2483. Min Act: -0.0000

Data Index: 1439387 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.7418. Min Act: -0.0000

Data Index: 60175 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.7062. Min Act: -0.0000

Data Index: 293676 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5264. Min Act: -0.0000

Data Index: 1507242 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.3615. Min Act: -0.0000

Data Index: 765434 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5046. Min Act: -0.0000

Data Index: 1962938 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5657. Min Act: -0.0000

Data Index: 485153 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5727. Min Act: -0.0000

Data Index: 1119145 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5320. Min Act: -0.0000

Data Index: 1027228 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5784. Min Act: -0.0000

Data Index: 776883 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.3667. Min Act: -0.0000

Data Index: 1278664 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5435. Min Act: -0.0000

Data Index: 1080280 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5567. Min Act: -0.0000

Data Index: 1157364 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.6082. Min Act: -0.0000

Data Index: 599429 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.3778. Min Act: -0.0000

Data Index: 1889568 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.1151. Min Act: -0.0000

Data Index: 1641528 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.4497. Min Act: -0.0000

Data Index: 1135444 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.3639. Min Act: -0.0000

Data Index: 189294 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.3684. Min Act: -0.0000

Data Index: 828488 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.2126. Min Act: -0.0000

Data Index: 1902662 (The Pile)

Max Activating Token Index: 213