Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 85 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1154432 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3385. Min Act: -0.0000

Data Index: 469743 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3298. Min Act: -0.0000

Data Index: 570217 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1120916 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2888. Min Act: -0.0001

Data Index: 1478232 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1872458 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2892. Min Act: -0.0000

Data Index: 404804 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2700. Min Act: -0.0000

Data Index: 415791 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2755. Min Act: -0.0000

Data Index: 547030 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1327778 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2695. Min Act: -0.0001

Data Index: 298798 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1544906 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2664. Min Act: -0.0000

Data Index: 45191 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2575. Min Act: -0.0000

Data Index: 241531 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1007334 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1213432 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2622. Min Act: -0.0000

Data Index: 485180 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2523. Min Act: -0.0000

Data Index: 248446 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1406592 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2497. Min Act: 0.0000

Data Index: 1148996 (The Pile)

Max Activating Token Index: 282