Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1607 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5569. Min Act: -0.1700

Data Index: 638404 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5681. Min Act: -0.1700

Data Index: 1616560 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5482. Min Act: -0.1700

Data Index: 2155486 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5671. Min Act: -0.1700

Data Index: 1724874 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5063. Min Act: -0.1700

Data Index: 2429410 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5041. Min Act: -0.1700

Data Index: 6360794 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5103. Min Act: -0.1700

Data Index: 3766479 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5083. Min Act: -0.1700

Data Index: 2661151 (Open Web Text)

Max Activating Token Index: 120

Text #8

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.5005. Min Act: -0.1700

Data Index: 8283429 (Open Web Text)

Max Activating Token Index: 417

Text #9

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4660. Min Act: -0.1700

Data Index: 5147317 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4840. Min Act: -0.1700

Data Index: 676934 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4700. Min Act: -0.1700

Data Index: 3671660 (Open Web Text)

Max Activating Token Index: 202

Text #12

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4736. Min Act: -0.1700

Data Index: 5485972 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4685. Min Act: -0.1700

Data Index: 1968773 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4688. Min Act: -0.1700

Data Index: 2178298 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4800. Min Act: -0.1700

Data Index: 5654665 (Open Web Text)

Max Activating Token Index: 108

Text #16

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4580. Min Act: -0.1700

Data Index: 6180773 (Open Web Text)

Max Activating Token Index: 927

Text #17

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4784. Min Act: -0.1700

Data Index: 639872 (Open Web Text)

Max Activating Token Index: 436

Text #18

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4840. Min Act: -0.1700

Data Index: 2309805 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 4.5681. Min Range: -4.5681

Max Act: 4.4905. Min Act: -0.1700

Data Index: 438798 (Open Web Text)

Max Activating Token Index: 192