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

Dataset: Open Web Text

Neuron 2867 in Layer 5

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: 5.0549. Min Range: -5.0549

Max Act: 5.0549. Min Act: -0.1700

Data Index: 2626570 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.9448. Min Act: -0.1700

Data Index: 1738995 (Open Web Text)

Max Activating Token Index: 870

Text #2

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.9006. Min Act: -0.1700

Data Index: 7844869 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.9084. Min Act: -0.1700

Data Index: 3115249 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.8399. Min Act: -0.1700

Data Index: 1025985 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.8320. Min Act: -0.1700

Data Index: 5417918 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7957. Min Act: -0.1700

Data Index: 1669183 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.8344. Min Act: -0.1700

Data Index: 8461928 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7859. Min Act: -0.1700

Data Index: 4104928 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.8019. Min Act: -0.1700

Data Index: 8622666 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7877. Min Act: -0.1700

Data Index: 3855869 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7885. Min Act: -0.1700

Data Index: 8244832 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.8129. Min Act: -0.1700

Data Index: 2440238 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7364. Min Act: -0.1700

Data Index: 4516476 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7624. Min Act: -0.1700

Data Index: 1417493 (Open Web Text)

Max Activating Token Index: 654

Text #15

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7386. Min Act: -0.1700

Data Index: 4368725 (Open Web Text)

Max Activating Token Index: 267

Text #16

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7725. Min Act: -0.1700

Data Index: 4085777 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.7497. Min Act: -0.1700

Data Index: 5269190 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.6939. Min Act: -0.1700

Data Index: 990216 (Open Web Text)

Max Activating Token Index: 661

Text #19

Max Range: 5.0549. Min Range: -5.0549

Max Act: 4.6949. Min Act: -0.1700

Data Index: 5812185 (Open Web Text)

Max Activating Token Index: 931