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

Dataset: Open Web Text

Neuron 138 in Layer 5

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: 2.6543. Min Range: -2.6543

Max Act: 2.6543. Min Act: -0.1700

Data Index: 3554767 (Open Web Text)

Max Activating Token Index: 900

Text #1

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.6281. Min Act: -0.1700

Data Index: 5095485 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5875. Min Act: -0.1700

Data Index: 2113174 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5844. Min Act: -0.1700

Data Index: 3438215 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5731. Min Act: -0.1700

Data Index: 7320969 (Open Web Text)

Max Activating Token Index: 772

Text #5

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5675. Min Act: -0.1700

Data Index: 8808595 (Open Web Text)

Max Activating Token Index: 271

Text #6

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5509. Min Act: -0.1700

Data Index: 5826836 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5188. Min Act: -0.1700

Data Index: 7546440 (Open Web Text)

Max Activating Token Index: 221

Text #8

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5220. Min Act: -0.1700

Data Index: 5979306 (Open Web Text)

Max Activating Token Index: 460

Text #9

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4956. Min Act: -0.1700

Data Index: 2621418 (Open Web Text)

Max Activating Token Index: 928

Text #10

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5011. Min Act: -0.1700

Data Index: 896660 (Open Web Text)

Max Activating Token Index: 97

Text #11

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4996. Min Act: -0.1700

Data Index: 1052943 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.5085. Min Act: -0.1700

Data Index: 5549615 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4761. Min Act: -0.1700

Data Index: 1117580 (Open Web Text)

Max Activating Token Index: 822

Text #14

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4920. Min Act: -0.1700

Data Index: 596773 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4902. Min Act: -0.1700

Data Index: 5436827 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4700. Min Act: -0.1700

Data Index: 3816426 (Open Web Text)

Max Activating Token Index: 763

Text #17

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4807. Min Act: -0.1700

Data Index: 8587523 (Open Web Text)

Max Activating Token Index: 699

Text #18

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4875. Min Act: -0.1700

Data Index: 6411463 (Open Web Text)

Max Activating Token Index: 849

Text #19

Max Range: 2.6543. Min Range: -2.6543

Max Act: 2.4651. Min Act: -0.1700

Data Index: 3232285 (Open Web Text)

Max Activating Token Index: 267