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

Dataset: The Pile

Neuron 2521 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: 0.9965. Min Range: -0.9965

Max Act: 0.9965. Min Act: -0.0000

Data Index: 1991937 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1218192 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.9062. Min Act: -0.0000

Data Index: 825468 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.7784. Min Act: -0.0000

Data Index: 503006 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1547661 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1313093 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.7817. Min Act: -0.0000

Data Index: 579123 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1725566 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.7095. Min Act: -0.0000

Data Index: 641978 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1216837 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1540656 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6771. Min Act: -0.0000

Data Index: 442594 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6707. Min Act: -0.0000

Data Index: 87630 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.7162. Min Act: -0.0000

Data Index: 513418 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1428715 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6941. Min Act: -0.0000

Data Index: 296061 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6218. Min Act: -0.0000

Data Index: 210943 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.7179. Min Act: -0.0000

Data Index: 306 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1471550 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 0.9965. Min Range: -0.9965

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1515951 (The Pile)

Max Activating Token Index: 680