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

Dataset: The Pile

Neuron 3688 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1755916 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1888940 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1955328 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1713962 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1067961 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1488081 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1158445 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5741. Min Act: -0.0000

Data Index: 229232 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6404. Min Act: -0.0000

Data Index: 707100 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6205. Min Act: -0.0000

Data Index: 945709 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1701496 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1028157 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1926312 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5653. Min Act: -0.0000

Data Index: 799458 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6076. Min Act: -0.0000

Data Index: 846034 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5960. Min Act: -0.0000

Data Index: 998064 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5937. Min Act: -0.0000

Data Index: 581387 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1280237 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6070. Min Act: -0.0000

Data Index: 968447 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5630. Min Act: -0.0000

Data Index: 363062 (The Pile)

Max Activating Token Index: 861