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

Dataset: Open Web Text

Neuron 2585 in Layer 6

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: 4.7516. Min Range: -4.7516

Max Act: 4.7516. Min Act: -0.1700

Data Index: 4838752 (Open Web Text)

Max Activating Token Index: 251

Text #1

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6562. Min Act: -0.1700

Data Index: 1185900 (Open Web Text)

Max Activating Token Index: 927

Text #2

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6185. Min Act: -0.1700

Data Index: 3745412 (Open Web Text)

Max Activating Token Index: 984

Text #3

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6300. Min Act: -0.1700

Data Index: 5171761 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6444. Min Act: -0.1700

Data Index: 7148135 (Open Web Text)

Max Activating Token Index: 367

Text #5

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6167. Min Act: -0.1700

Data Index: 4114151 (Open Web Text)

Max Activating Token Index: 959

Text #6

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6001. Min Act: -0.1700

Data Index: 7292282 (Open Web Text)

Max Activating Token Index: 170

Text #7

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5961. Min Act: -0.1700

Data Index: 6936350 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5972. Min Act: -0.1700

Data Index: 5934311 (Open Web Text)

Max Activating Token Index: 949

Text #9

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5986. Min Act: -0.1700

Data Index: 778649 (Open Web Text)

Max Activating Token Index: 826

Text #10

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.6056. Min Act: -0.1700

Data Index: 5788950 (Open Web Text)

Max Activating Token Index: 453

Text #11

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5446. Min Act: -0.1700

Data Index: 57217 (Open Web Text)

Max Activating Token Index: 924

Text #12

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5765. Min Act: -0.1700

Data Index: 5804104 (Open Web Text)

Max Activating Token Index: 816

Text #13

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5751. Min Act: -0.1700

Data Index: 6566644 (Open Web Text)

Max Activating Token Index: 481

Text #14

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5710. Min Act: -0.1700

Data Index: 5722989 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5771. Min Act: -0.1700

Data Index: 1443372 (Open Web Text)

Max Activating Token Index: 755

Text #16

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5766. Min Act: -0.1700

Data Index: 8577984 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5753. Min Act: -0.1700

Data Index: 4251632 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5299. Min Act: -0.1700

Data Index: 4814356 (Open Web Text)

Max Activating Token Index: 342

Text #19

Max Range: 4.7516. Min Range: -4.7516

Max Act: 4.5401. Min Act: -0.1700

Data Index: 705440 (Open Web Text)

Max Activating Token Index: 814