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

Dataset: Open Web Text

Neuron 1807 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: 4.0514. Min Range: -4.0514

Max Act: 4.0514. Min Act: -0.1700

Data Index: 1658099 (Open Web Text)

Max Activating Token Index: 643

Text #1

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.9961. Min Act: -0.1700

Data Index: 8334850 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.9777. Min Act: -0.1700

Data Index: 5543138 (Open Web Text)

Max Activating Token Index: 419

Text #3

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.9456. Min Act: -0.1700

Data Index: 2454429 (Open Web Text)

Max Activating Token Index: 1000

Text #4

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.9088. Min Act: -0.1700

Data Index: 3039713 (Open Web Text)

Max Activating Token Index: 924

Text #5

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8950. Min Act: -0.1700

Data Index: 400280 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.9073. Min Act: -0.1700

Data Index: 3913977 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8818. Min Act: -0.1700

Data Index: 6607578 (Open Web Text)

Max Activating Token Index: 139

Text #8

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8815. Min Act: -0.1700

Data Index: 4127331 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8893. Min Act: -0.1700

Data Index: 4502183 (Open Web Text)

Max Activating Token Index: 960

Text #10

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8369. Min Act: -0.1700

Data Index: 7847667 (Open Web Text)

Max Activating Token Index: 976

Text #11

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8235. Min Act: -0.1700

Data Index: 8778162 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8729. Min Act: -0.1700

Data Index: 1431596 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8304. Min Act: -0.1700

Data Index: 8010596 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8385. Min Act: -0.1700

Data Index: 8709199 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8244. Min Act: -0.1700

Data Index: 1137213 (Open Web Text)

Max Activating Token Index: 882

Text #16

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8134. Min Act: -0.1700

Data Index: 8274594 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8179. Min Act: -0.1700

Data Index: 577913 (Open Web Text)

Max Activating Token Index: 968

Text #18

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8114. Min Act: -0.1700

Data Index: 3423533 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.8090. Min Act: -0.1700

Data Index: 7190793 (Open Web Text)

Max Activating Token Index: 1005