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

Dataset: Open Web Text

Neuron 878 in Layer 4

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: 2.7931. Min Range: -2.7931

Max Act: 2.7931. Min Act: -0.1700

Data Index: 7003521 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7671. Min Act: -0.1700

Data Index: 1676017 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7574. Min Act: -0.1700

Data Index: 1674129 (Open Web Text)

Max Activating Token Index: 984

Text #3

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7694. Min Act: -0.1700

Data Index: 1451291 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7438. Min Act: -0.1700

Data Index: 7788477 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7458. Min Act: -0.1700

Data Index: 973427 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7327. Min Act: -0.1700

Data Index: 7675930 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7084. Min Act: -0.1700

Data Index: 6788570 (Open Web Text)

Max Activating Token Index: 763

Text #8

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7168. Min Act: -0.1700

Data Index: 1042886 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6959. Min Act: -0.1700

Data Index: 3561724 (Open Web Text)

Max Activating Token Index: 244

Text #10

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.7031. Min Act: -0.1700

Data Index: 7694847 (Open Web Text)

Max Activating Token Index: 528

Text #11

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6750. Min Act: -0.1700

Data Index: 5214297 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6653. Min Act: -0.1700

Data Index: 3400988 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6538. Min Act: -0.1700

Data Index: 4931680 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6543. Min Act: -0.1700

Data Index: 1190667 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6642. Min Act: -0.1700

Data Index: 6417114 (Open Web Text)

Max Activating Token Index: 814

Text #16

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6577. Min Act: -0.1700

Data Index: 4976305 (Open Web Text)

Max Activating Token Index: 49

Text #17

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6651. Min Act: -0.1700

Data Index: 5479558 (Open Web Text)

Max Activating Token Index: 395

Text #18

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6518. Min Act: -0.1700

Data Index: 1017979 (Open Web Text)

Max Activating Token Index: 923

Text #19

Max Range: 2.7931. Min Range: -2.7931

Max Act: 2.6506. Min Act: -0.1700

Data Index: 1118329 (Open Web Text)

Max Activating Token Index: 866