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

Dataset: Open Web Text

Neuron 672 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: 4.7887. Min Range: -4.7887

Max Act: 4.7887. Min Act: -0.1700

Data Index: 1736092 (Open Web Text)

Max Activating Token Index: 980

Text #1

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.5128. Min Act: -0.1700

Data Index: 4872060 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4935. Min Act: -0.1700

Data Index: 37830 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.5161. Min Act: -0.1700

Data Index: 7520702 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4709. Min Act: -0.1700

Data Index: 3606859 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4807. Min Act: -0.1700

Data Index: 8099891 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4560. Min Act: -0.1700

Data Index: 5233834 (Open Web Text)

Max Activating Token Index: 900

Text #7

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4703. Min Act: -0.1700

Data Index: 3171722 (Open Web Text)

Max Activating Token Index: 213

Text #8

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4268. Min Act: -0.1700

Data Index: 726244 (Open Web Text)

Max Activating Token Index: 308

Text #9

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4651. Min Act: -0.1700

Data Index: 1511911 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4745. Min Act: -0.1700

Data Index: 4929766 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4419. Min Act: -0.1700

Data Index: 1629125 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4020. Min Act: -0.1700

Data Index: 8133141 (Open Web Text)

Max Activating Token Index: 845

Text #13

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.3991. Min Act: -0.1700

Data Index: 886716 (Open Web Text)

Max Activating Token Index: 877

Text #14

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4322. Min Act: -0.1700

Data Index: 1255236 (Open Web Text)

Max Activating Token Index: 574

Text #15

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.3540. Min Act: -0.1700

Data Index: 2815172 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.3937. Min Act: -0.1700

Data Index: 5716739 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.3745. Min Act: -0.1700

Data Index: 4358776 (Open Web Text)

Max Activating Token Index: 126

Text #18

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.4063. Min Act: -0.1700

Data Index: 6913450 (Open Web Text)

Max Activating Token Index: 949

Text #19

Max Range: 4.7887. Min Range: -4.7887

Max Act: 4.3927. Min Act: -0.1700

Data Index: 1727303 (Open Web Text)

Max Activating Token Index: 288