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

Dataset: Open Web Text

Neuron 2673 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: 4.0181. Min Range: -4.0181

Max Act: 4.0181. Min Act: -0.1700

Data Index: 8478692 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9440. Min Act: -0.1700

Data Index: 2572884 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9552. Min Act: -0.1700

Data Index: 2572887 (Open Web Text)

Max Activating Token Index: 407

Text #3

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9116. Min Act: -0.1700

Data Index: 5323321 (Open Web Text)

Max Activating Token Index: 974

Text #4

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9377. Min Act: -0.1700

Data Index: 1163740 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8867. Min Act: -0.1700

Data Index: 5552204 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9147. Min Act: -0.1700

Data Index: 2839272 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8886. Min Act: -0.1700

Data Index: 5446949 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8970. Min Act: -0.1700

Data Index: 8489109 (Open Web Text)

Max Activating Token Index: 673

Text #9

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8976. Min Act: -0.1700

Data Index: 2445433 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8967. Min Act: -0.1700

Data Index: 1055478 (Open Web Text)

Max Activating Token Index: 103

Text #11

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9168. Min Act: -0.1700

Data Index: 7147087 (Open Web Text)

Max Activating Token Index: 600

Text #12

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9079. Min Act: -0.1700

Data Index: 195271 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8475. Min Act: -0.1700

Data Index: 4999219 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8594. Min Act: -0.1700

Data Index: 4229406 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.9177. Min Act: -0.1700

Data Index: 8828152 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8822. Min Act: -0.1700

Data Index: 3816985 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8701. Min Act: -0.1700

Data Index: 1616446 (Open Web Text)

Max Activating Token Index: 1013

Text #18

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8373. Min Act: -0.1700

Data Index: 3213845 (Open Web Text)

Max Activating Token Index: 84

Text #19

Max Range: 4.0181. Min Range: -4.0181

Max Act: 3.8651. Min Act: -0.1700

Data Index: 1168291 (Open Web Text)

Max Activating Token Index: 611