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

Dataset: Open Web Text

Neuron 588 in Layer 4

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: 3.8758. Min Range: -3.8758

Max Act: 3.8758. Min Act: -0.1700

Data Index: 3989828 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.8674. Min Act: -0.1700

Data Index: 94282 (Open Web Text)

Max Activating Token Index: 694

Text #2

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.8492. Min Act: -0.1700

Data Index: 7949198 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.8475. Min Act: -0.1700

Data Index: 6945171 (Open Web Text)

Max Activating Token Index: 243

Text #4

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.8373. Min Act: -0.1700

Data Index: 6267181 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7652. Min Act: -0.1700

Data Index: 1941553 (Open Web Text)

Max Activating Token Index: 222

Text #6

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.8077. Min Act: -0.1700

Data Index: 7576280 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7858. Min Act: -0.1700

Data Index: 3460199 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.8043. Min Act: -0.1700

Data Index: 6882441 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1292353 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7797. Min Act: -0.1700

Data Index: 4775121 (Open Web Text)

Max Activating Token Index: 347

Text #11

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7860. Min Act: -0.1700

Data Index: 5689289 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7787. Min Act: -0.1700

Data Index: 6830885 (Open Web Text)

Max Activating Token Index: 202

Text #13

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7530. Min Act: -0.1700

Data Index: 3195707 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7441. Min Act: -0.1700

Data Index: 6642984 (Open Web Text)

Max Activating Token Index: 399

Text #15

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7589. Min Act: -0.1700

Data Index: 1069458 (Open Web Text)

Max Activating Token Index: 233

Text #16

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7599. Min Act: -0.1700

Data Index: 3113836 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7675. Min Act: -0.1700

Data Index: 6027270 (Open Web Text)

Max Activating Token Index: 511

Text #18

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7584. Min Act: -0.1700

Data Index: 7292360 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 3.8758. Min Range: -3.8758

Max Act: 3.7744. Min Act: -0.1700

Data Index: 5606515 (Open Web Text)

Max Activating Token Index: 457