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

Dataset: Open Web Text

Neuron 423 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: 4.5960. Min Range: -4.5960

Max Act: 4.5960. Min Act: -0.1700

Data Index: 6702303 (Open Web Text)

Max Activating Token Index: 903

Text #1

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.5601. Min Act: -0.1700

Data Index: 5205198 (Open Web Text)

Max Activating Token Index: 703

Text #2

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.5300. Min Act: -0.1700

Data Index: 5661517 (Open Web Text)

Max Activating Token Index: 190

Text #3

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.4367. Min Act: -0.1700

Data Index: 3204143 (Open Web Text)

Max Activating Token Index: 779

Text #4

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3835. Min Act: -0.1700

Data Index: 4824982 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.4048. Min Act: -0.1700

Data Index: 6441476 (Open Web Text)

Max Activating Token Index: 831

Text #6

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3813. Min Act: -0.1700

Data Index: 4246115 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3972. Min Act: -0.1700

Data Index: 3744078 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3823. Min Act: -0.1700

Data Index: 3282287 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3446. Min Act: -0.1700

Data Index: 1222544 (Open Web Text)

Max Activating Token Index: 610

Text #10

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3702. Min Act: -0.1700

Data Index: 1939996 (Open Web Text)

Max Activating Token Index: 443

Text #11

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3710. Min Act: -0.1700

Data Index: 6041315 (Open Web Text)

Max Activating Token Index: 472

Text #12

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3253. Min Act: -0.1700

Data Index: 2868874 (Open Web Text)

Max Activating Token Index: 424

Text #13

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3347. Min Act: -0.1700

Data Index: 4421695 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3157. Min Act: -0.1700

Data Index: 1808928 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3174. Min Act: -0.1700

Data Index: 2957272 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3259. Min Act: -0.1700

Data Index: 5815367 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3035. Min Act: -0.1700

Data Index: 544770 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3330. Min Act: -0.1700

Data Index: 4415976 (Open Web Text)

Max Activating Token Index: 525

Text #19

Max Range: 4.5960. Min Range: -4.5960

Max Act: 4.3367. Min Act: -0.1700

Data Index: 606323 (Open Web Text)

Max Activating Token Index: 969