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

Dataset: Open Web Text

Neuron 2115 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: 4.4261. Min Range: -4.4261

Max Act: 4.4261. Min Act: -0.1700

Data Index: 836255 (Open Web Text)

Max Activating Token Index: 588

Text #1

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.2171. Min Act: -0.1700

Data Index: 7079939 (Open Web Text)

Max Activating Token Index: 104

Text #2

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.1907. Min Act: -0.1700

Data Index: 1499923 (Open Web Text)

Max Activating Token Index: 975

Text #3

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.1420. Min Act: -0.1700

Data Index: 1338430 (Open Web Text)

Max Activating Token Index: 866

Text #4

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.1310. Min Act: -0.1700

Data Index: 2402551 (Open Web Text)

Max Activating Token Index: 838

Text #5

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.1106. Min Act: -0.1700

Data Index: 3533738 (Open Web Text)

Max Activating Token Index: 969

Text #6

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0835. Min Act: -0.1700

Data Index: 3105123 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0576. Min Act: -0.1700

Data Index: 5238077 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0967. Min Act: -0.1700

Data Index: 5341788 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.1131. Min Act: -0.1700

Data Index: 8701179 (Open Web Text)

Max Activating Token Index: 771

Text #10

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0280. Min Act: -0.1700

Data Index: 1889018 (Open Web Text)

Max Activating Token Index: 824

Text #11

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0348. Min Act: -0.1700

Data Index: 7734303 (Open Web Text)

Max Activating Token Index: 772

Text #12

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0291. Min Act: -0.1700

Data Index: 1496029 (Open Web Text)

Max Activating Token Index: 813

Text #13

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0097. Min Act: -0.1700

Data Index: 1549524 (Open Web Text)

Max Activating Token Index: 369

Text #14

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0108. Min Act: -0.1700

Data Index: 754503 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 4.4261. Min Range: -4.4261

Max Act: 3.9926. Min Act: -0.1700

Data Index: 1436396 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0001. Min Act: -0.1700

Data Index: 8237670 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0123. Min Act: -0.1700

Data Index: 2639640 (Open Web Text)

Max Activating Token Index: 331

Text #18

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0031. Min Act: -0.1700

Data Index: 5564693 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 4.4261. Min Range: -4.4261

Max Act: 4.0031. Min Act: -0.1700

Data Index: 1629946 (Open Web Text)

Max Activating Token Index: 1005