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

Dataset: Open Web Text

Neuron 1761 in Layer 0

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: 3.1089. Min Range: -3.1089

Max Act: 3.1089. Min Act: -0.1700

Data Index: 4022184 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0958. Min Act: -0.1700

Data Index: 7448145 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0572. Min Act: -0.1700

Data Index: 3539894 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0340. Min Act: -0.1700

Data Index: 5642256 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0364. Min Act: -0.1700

Data Index: 2544807 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0328. Min Act: -0.1700

Data Index: 3251380 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0252. Min Act: -0.1700

Data Index: 4782797 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0173. Min Act: -0.1700

Data Index: 323359 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0129. Min Act: -0.1700

Data Index: 8704325 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0171. Min Act: -0.1700

Data Index: 6475529 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.1089. Min Range: -3.1089

Max Act: 2.9967. Min Act: -0.1700

Data Index: 8695575 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0092. Min Act: -0.1700

Data Index: 7840864 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0029. Min Act: -0.1700

Data Index: 356780 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0009. Min Act: -0.1700

Data Index: 5980870 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0090. Min Act: -0.1700

Data Index: 1076669 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0085. Min Act: -0.1700

Data Index: 4952592 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.1089. Min Range: -3.1089

Max Act: 3.0021. Min Act: -0.1700

Data Index: 4816322 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.1089. Min Range: -3.1089

Max Act: 2.9892. Min Act: -0.1700

Data Index: 7498524 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1089. Min Range: -3.1089

Max Act: 2.9828. Min Act: -0.1700

Data Index: 323220 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.1089. Min Range: -3.1089

Max Act: 2.9828. Min Act: -0.1700

Data Index: 4387527 (Open Web Text)

Max Activating Token Index: 4