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

Dataset: Open Web Text

Neuron 1591 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: 4.3687. Min Range: -4.3687

Max Act: 4.3687. Min Act: -0.1700

Data Index: 1493396 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0875. Min Act: -0.1700

Data Index: 4123988 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.0110. Min Act: -0.1700

Data Index: 832070 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.9568. Min Act: -0.1700

Data Index: 5797772 (Open Web Text)

Max Activating Token Index: 820

Text #4

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8993. Min Act: -0.1700

Data Index: 2859648 (Open Web Text)

Max Activating Token Index: 443

Text #5

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.9249. Min Act: -0.1700

Data Index: 2013848 (Open Web Text)

Max Activating Token Index: 563

Text #6

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8708. Min Act: -0.1700

Data Index: 1805464 (Open Web Text)

Max Activating Token Index: 978

Text #7

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8494. Min Act: -0.1700

Data Index: 7847847 (Open Web Text)

Max Activating Token Index: 614

Text #8

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8982. Min Act: -0.1700

Data Index: 3307368 (Open Web Text)

Max Activating Token Index: 487

Text #9

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8158. Min Act: -0.1700

Data Index: 7693439 (Open Web Text)

Max Activating Token Index: 815

Text #10

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.7335. Min Act: -0.1700

Data Index: 4568514 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8169. Min Act: -0.1700

Data Index: 7436996 (Open Web Text)

Max Activating Token Index: 73

Text #12

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8585. Min Act: -0.1700

Data Index: 5501575 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.8078. Min Act: -0.1700

Data Index: 6561380 (Open Web Text)

Max Activating Token Index: 511

Text #14

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.7969. Min Act: -0.1700

Data Index: 6726621 (Open Web Text)

Max Activating Token Index: 942

Text #15

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.7760. Min Act: -0.1700

Data Index: 6133255 (Open Web Text)

Max Activating Token Index: 263

Text #16

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.7368. Min Act: -0.1700

Data Index: 5897270 (Open Web Text)

Max Activating Token Index: 619

Text #17

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.7446. Min Act: -0.1700

Data Index: 1174867 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.7979. Min Act: -0.1700

Data Index: 7217447 (Open Web Text)

Max Activating Token Index: 610

Text #19

Max Range: 4.3687. Min Range: -4.3687

Max Act: 3.7294. Min Act: -0.1700

Data Index: 3455443 (Open Web Text)

Max Activating Token Index: 771