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

Dataset: Open Web Text

Neuron 940 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: 3.1960. Min Range: -3.1960

Max Act: 3.1906. Min Act: -0.1700

Data Index: 1057291 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1956. Min Act: -0.1700

Data Index: 5580116 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1960. Min Act: -0.1700

Data Index: 4048331 (Open Web Text)

Max Activating Token Index: 306

Text #3

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1957. Min Act: -0.1700

Data Index: 2010083 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1660. Min Act: -0.1700

Data Index: 4529601 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1804. Min Act: -0.1700

Data Index: 3641343 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1680. Min Act: -0.1700

Data Index: 503254 (Open Web Text)

Max Activating Token Index: 71

Text #7

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1842. Min Act: -0.1700

Data Index: 5006700 (Open Web Text)

Max Activating Token Index: 43

Text #8

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1761. Min Act: -0.1700

Data Index: 4114370 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1388. Min Act: -0.1700

Data Index: 3299916 (Open Web Text)

Max Activating Token Index: 642

Text #10

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1262. Min Act: -0.1700

Data Index: 2649353 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1287. Min Act: -0.1700

Data Index: 703922 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1189. Min Act: -0.1700

Data Index: 4529602 (Open Web Text)

Max Activating Token Index: 87

Text #13

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0903. Min Act: -0.1700

Data Index: 7819494 (Open Web Text)

Max Activating Token Index: 971

Text #14

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0981. Min Act: -0.1700

Data Index: 5242912 (Open Web Text)

Max Activating Token Index: 1003

Text #15

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1038. Min Act: -0.1700

Data Index: 8306412 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0935. Min Act: -0.1700

Data Index: 1074810 (Open Web Text)

Max Activating Token Index: 858

Text #17

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1017. Min Act: -0.1700

Data Index: 7094451 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0981. Min Act: -0.1700

Data Index: 6779408 (Open Web Text)

Max Activating Token Index: 890

Text #19

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1016. Min Act: -0.1700

Data Index: 6157815 (Open Web Text)

Max Activating Token Index: 975