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

Dataset: Open Web Text

Neuron 1650 in Layer 1

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: 3.0512. Min Range: -3.0512

Max Act: 3.0512. Min Act: -0.1700

Data Index: 6083192 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.9947. Min Act: -0.1700

Data Index: 295006 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.9617. Min Act: -0.1700

Data Index: 3995986 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.9327. Min Act: -0.1700

Data Index: 4485746 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8969. Min Act: -0.1700

Data Index: 3698141 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8960. Min Act: -0.1700

Data Index: 620189 (Open Web Text)

Max Activating Token Index: 523

Text #6

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8939. Min Act: -0.1700

Data Index: 7892911 (Open Web Text)

Max Activating Token Index: 171

Text #7

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8673. Min Act: -0.1700

Data Index: 2604451 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8801. Min Act: -0.1700

Data Index: 4969042 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8481. Min Act: -0.1700

Data Index: 6042429 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8359. Min Act: -0.1700

Data Index: 3995987 (Open Web Text)

Max Activating Token Index: 159

Text #11

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8129. Min Act: -0.1700

Data Index: 1362951 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8109. Min Act: -0.1700

Data Index: 2526745 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8121. Min Act: -0.1700

Data Index: 7723536 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8070. Min Act: -0.1700

Data Index: 7607622 (Open Web Text)

Max Activating Token Index: 195

Text #15

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8193. Min Act: -0.1700

Data Index: 7137657 (Open Web Text)

Max Activating Token Index: 145

Text #16

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8264. Min Act: -0.1700

Data Index: 1804451 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8018. Min Act: -0.1700

Data Index: 6837516 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.7985. Min Act: -0.1700

Data Index: 3995988 (Open Web Text)

Max Activating Token Index: 157

Text #19

Max Range: 3.0512. Min Range: -3.0512

Max Act: 2.8072. Min Act: -0.1700

Data Index: 1621755 (Open Web Text)

Max Activating Token Index: 554