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

Dataset: Open Web Text

Neuron 1009 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: 1.4126. Min Range: -1.4126

Max Act: 1.4126. Min Act: -0.1700

Data Index: 4456622 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3694. Min Act: -0.1700

Data Index: 7436799 (Open Web Text)

Max Activating Token Index: 575

Text #2

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3869. Min Act: -0.1700

Data Index: 4645844 (Open Web Text)

Max Activating Token Index: 583

Text #3

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3821. Min Act: -0.1700

Data Index: 1258778 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3726. Min Act: -0.1700

Data Index: 588841 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3556. Min Act: -0.1700

Data Index: 5128015 (Open Web Text)

Max Activating Token Index: 589

Text #6

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3559. Min Act: -0.1700

Data Index: 5181327 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3509. Min Act: -0.1700

Data Index: 7624594 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3389. Min Act: -0.1700

Data Index: 1258774 (Open Web Text)

Max Activating Token Index: 572

Text #9

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3371. Min Act: -0.1700

Data Index: 381796 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3469. Min Act: -0.1700

Data Index: 6299059 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3435. Min Act: -0.1700

Data Index: 5009400 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3190. Min Act: -0.1700

Data Index: 718410 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3170. Min Act: -0.1700

Data Index: 5176633 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3124. Min Act: -0.1700

Data Index: 1081142 (Open Web Text)

Max Activating Token Index: 582

Text #15

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3065. Min Act: -0.1700

Data Index: 8655890 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.2996. Min Act: -0.1700

Data Index: 5306300 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.3068. Min Act: -0.1700

Data Index: 7624603 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.2959. Min Act: -0.1700

Data Index: 3020004 (Open Web Text)

Max Activating Token Index: 558

Text #19

Max Range: 1.4126. Min Range: -1.4126

Max Act: 1.2994. Min Act: -0.1700

Data Index: 6328792 (Open Web Text)

Max Activating Token Index: 541