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

Dataset: The Pile

Neuron 4943 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1266596 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0089. Min Act: -0.0000

Data Index: 134654 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1919561 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8538. Min Act: -0.0000

Data Index: 599723 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8880. Min Act: -0.0000

Data Index: 821376 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1555045 (The Pile)

Max Activating Token Index: 474

Text #6

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1398884 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8403. Min Act: -0.0000

Data Index: 761642 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7965. Min Act: -0.0000

Data Index: 318741 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1949041 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1799032 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8552. Min Act: -0.0000

Data Index: 458972 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1503274 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7632. Min Act: -0.0000

Data Index: 740654 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1098511 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1177062 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7377. Min Act: -0.0000

Data Index: 309403 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7231. Min Act: -0.0000

Data Index: 585043 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1021317 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1502439 (The Pile)

Max Activating Token Index: 237