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

Dataset: Open Web Text

Neuron 1115 in Layer 3

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: 3.4024. Min Range: -3.4024

Max Act: 3.4024. Min Act: -0.1700

Data Index: 8647444 (Open Web Text)

Max Activating Token Index: 877

Text #1

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.3997. Min Act: -0.1700

Data Index: 4830614 (Open Web Text)

Max Activating Token Index: 116

Text #2

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.2475. Min Act: -0.1700

Data Index: 3709098 (Open Web Text)

Max Activating Token Index: 435

Text #3

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.2413. Min Act: -0.1700

Data Index: 3037098 (Open Web Text)

Max Activating Token Index: 744

Text #4

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1876. Min Act: -0.1700

Data Index: 2462506 (Open Web Text)

Max Activating Token Index: 89

Text #5

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1520. Min Act: -0.1700

Data Index: 85202 (Open Web Text)

Max Activating Token Index: 130

Text #6

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1634. Min Act: -0.1700

Data Index: 1806454 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1756. Min Act: -0.1700

Data Index: 4555164 (Open Web Text)

Max Activating Token Index: 69

Text #8

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1159. Min Act: -0.1700

Data Index: 2367955 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1081. Min Act: -0.1700

Data Index: 450455 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.0976. Min Act: -0.1700

Data Index: 8625431 (Open Web Text)

Max Activating Token Index: 663

Text #11

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1217. Min Act: -0.1700

Data Index: 6527623 (Open Web Text)

Max Activating Token Index: 717

Text #12

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1170. Min Act: -0.1700

Data Index: 5599839 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1166. Min Act: -0.1700

Data Index: 3979818 (Open Web Text)

Max Activating Token Index: 988

Text #14

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.1068. Min Act: -0.1700

Data Index: 7967366 (Open Web Text)

Max Activating Token Index: 209

Text #15

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.0975. Min Act: -0.1700

Data Index: 6437430 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.0756. Min Act: -0.1700

Data Index: 8432951 (Open Web Text)

Max Activating Token Index: 587

Text #17

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.0932. Min Act: -0.1700

Data Index: 5432080 (Open Web Text)

Max Activating Token Index: 722

Text #18

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.0727. Min Act: -0.1700

Data Index: 5340847 (Open Web Text)

Max Activating Token Index: 373

Text #19

Max Range: 3.4024. Min Range: -3.4024

Max Act: 3.0851. Min Act: -0.1700

Data Index: 381679 (Open Web Text)

Max Activating Token Index: 753