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

Dataset: Open Web Text

Neuron 984 in Layer 0

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: 3.3082. Min Range: -3.3082

Max Act: 3.3082. Min Act: -0.1700

Data Index: 3793557 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2721. Min Act: -0.1700

Data Index: 2432354 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2511. Min Act: -0.1700

Data Index: 5039042 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2582. Min Act: -0.1700

Data Index: 5762674 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2419. Min Act: -0.1700

Data Index: 6312579 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2483. Min Act: -0.1700

Data Index: 4795277 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2310. Min Act: -0.1700

Data Index: 239654 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1989. Min Act: -0.1700

Data Index: 1804317 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2082. Min Act: -0.1700

Data Index: 8066608 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.2044. Min Act: -0.1700

Data Index: 4230896 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1823. Min Act: -0.1700

Data Index: 526227 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1797. Min Act: -0.1700

Data Index: 6001645 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1786. Min Act: -0.1700

Data Index: 5450207 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1680. Min Act: -0.1700

Data Index: 6234251 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1652. Min Act: -0.1700

Data Index: 7908888 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1428. Min Act: -0.1700

Data Index: 755165 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1402. Min Act: -0.1700

Data Index: 4811361 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1462. Min Act: -0.1700

Data Index: 2945056 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1415. Min Act: -0.1700

Data Index: 3732286 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.1487. Min Act: -0.1700

Data Index: 1282139 (Open Web Text)

Max Activating Token Index: 3