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

Dataset: The Pile

Neuron 204 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: 0.6499. Min Range: -0.6499

Max Act: 0.6323. Min Act: -0.0000

Data Index: 716174 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1846835 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6149. Min Act: -0.0000

Data Index: 535355 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1975797 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5884. Min Act: -0.0000

Data Index: 484779 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5524. Min Act: -0.0000

Data Index: 292461 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1957616 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5467. Min Act: 0.0000

Data Index: 1023102 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1906541 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5102. Min Act: -0.0000

Data Index: 260880 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1337014 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.5018. Min Act: -0.0000

Data Index: 507777 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4835. Min Act: -0.0000

Data Index: 521042 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4702. Min Act: -0.0000

Data Index: 196773 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1049215 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4644. Min Act: -0.0000

Data Index: 152916 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4433. Min Act: -0.0000

Data Index: 300304 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4347. Min Act: -0.0000

Data Index: 56890 (The Pile)

Max Activating Token Index: 647

Text #18

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1505549 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 0.6499. Min Range: -0.6499

Max Act: 0.4330. Min Act: -0.0000

Data Index: 326681 (The Pile)

Max Activating Token Index: 213