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

Dataset: The Pile

Neuron 3596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5780. Min Act: -0.0000

Data Index: 668689 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5174. Min Act: -0.0000

Data Index: 326729 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1012650 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1582544 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4310. Min Act: -0.0000

Data Index: 599095 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3874. Min Act: -0.0000

Data Index: 621962 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4439. Min Act: -0.0000

Data Index: 502121 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1204151 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3696. Min Act: -0.0000

Data Index: 972306 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1327217 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1618001 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1880131 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1558738 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1810680 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4050. Min Act: -0.0000

Data Index: 8174 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1758935 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1159073 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3877. Min Act: -0.0000

Data Index: 448758 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3955. Min Act: -0.0000

Data Index: 555317 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 0.5780. Min Range: -0.5780

Max Act: 0.3728. Min Act: -0.0000

Data Index: 144352 (The Pile)

Max Activating Token Index: 603