Model: None

Dataset: The Pile

Neuron 615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')

Text #0

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.2971. Min Act: -0.1700

Data Index: 6056027 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.2500. Min Act: -0.1700

Data Index: 2258168 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.8710. Min Act: -0.1700

Data Index: 3025617 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.3285. Min Act: -0.1700

Data Index: 4478009 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1083. Min Act: -0.1700

Data Index: 333941 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.3442. Min Act: -0.1700

Data Index: 8766088 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.7915. Min Act: -0.1700

Data Index: 1084053 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9186. Min Act: -0.1696

Data Index: 8331177 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1398. Min Act: -0.1700

Data Index: 9580716 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.5833. Min Act: -0.1700

Data Index: 6281421 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1241. Min Act: -0.1700

Data Index: 4144274 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.7915. Min Act: -0.1700

Data Index: 6660155 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9662. Min Act: -0.1700

Data Index: 4657461 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0294. Min Act: -0.1700

Data Index: 8598617 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0452. Min Act: -0.1686

Data Index: 6646866 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0610. Min Act: -0.1700

Data Index: 2977797 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0768. Min Act: -0.1696

Data Index: 2792448 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.7756. Min Act: -0.1700

Data Index: 7147160 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0452. Min Act: -0.1700

Data Index: 4087447 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0136. Min Act: -0.1700

Data Index: 4964494 (The Pile)

Max Activating Token Index: 226