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

Dataset: Open Web Text

Neuron 2112 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: 3.2786. Min Range: -3.2786

Max Act: 3.2786. Min Act: -0.1700

Data Index: 1104349 (Open Web Text)

Max Activating Token Index: 442

Text #1

Max Range: 3.2786. Min Range: -3.2786

Max Act: 3.0530. Min Act: -0.1700

Data Index: 3275317 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 3.2786. Min Range: -3.2786

Max Act: 3.0350. Min Act: -0.1700

Data Index: 3541964 (Open Web Text)

Max Activating Token Index: 83

Text #3

Max Range: 3.2786. Min Range: -3.2786

Max Act: 3.0125. Min Act: -0.1700

Data Index: 7083852 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 3.2786. Min Range: -3.2786

Max Act: 3.0218. Min Act: -0.1700

Data Index: 8272852 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.9948. Min Act: -0.1700

Data Index: 2105470 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.9644. Min Act: -0.1700

Data Index: 5418832 (Open Web Text)

Max Activating Token Index: 197

Text #7

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.9364. Min Act: -0.1700

Data Index: 180392 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.9423. Min Act: -0.1700

Data Index: 6305524 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.9140. Min Act: -0.1700

Data Index: 5364225 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8876. Min Act: -0.1700

Data Index: 8339877 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8948. Min Act: -0.1700

Data Index: 5702411 (Open Web Text)

Max Activating Token Index: 81

Text #12

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8827. Min Act: -0.1700

Data Index: 6832806 (Open Web Text)

Max Activating Token Index: 550

Text #13

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.9029. Min Act: -0.1700

Data Index: 7173719 (Open Web Text)

Max Activating Token Index: 849

Text #14

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8769. Min Act: -0.1700

Data Index: 1082256 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8690. Min Act: -0.1700

Data Index: 7350927 (Open Web Text)

Max Activating Token Index: 361

Text #16

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8700. Min Act: -0.1700

Data Index: 1547334 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8797. Min Act: -0.1700

Data Index: 8116853 (Open Web Text)

Max Activating Token Index: 325

Text #18

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8793. Min Act: -0.1700

Data Index: 6103524 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 3.2786. Min Range: -3.2786

Max Act: 2.8723. Min Act: -0.1700

Data Index: 6806890 (Open Web Text)

Max Activating Token Index: 104