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

Dataset: Open Web Text

Neuron 443 in Layer 5

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: 4.2034. Min Range: -4.2034

Max Act: 4.2034. Min Act: -0.1700

Data Index: 6149936 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 4.2034. Min Range: -4.2034

Max Act: 4.1906. Min Act: -0.1700

Data Index: 5098972 (Open Web Text)

Max Activating Token Index: 417

Text #2

Max Range: 4.2034. Min Range: -4.2034

Max Act: 4.0204. Min Act: -0.1700

Data Index: 3611924 (Open Web Text)

Max Activating Token Index: 897

Text #3

Max Range: 4.2034. Min Range: -4.2034

Max Act: 4.0234. Min Act: -0.1700

Data Index: 436592 (Open Web Text)

Max Activating Token Index: 861

Text #4

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.9673. Min Act: -0.1700

Data Index: 7267952 (Open Web Text)

Max Activating Token Index: 82

Text #5

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.9320. Min Act: -0.1700

Data Index: 2436409 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.9556. Min Act: -0.1700

Data Index: 3647976 (Open Web Text)

Max Activating Token Index: 96

Text #7

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.9211. Min Act: -0.1700

Data Index: 3567272 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8725. Min Act: -0.1700

Data Index: 7896512 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8813. Min Act: -0.1700

Data Index: 912526 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8613. Min Act: -0.1700

Data Index: 3749031 (Open Web Text)

Max Activating Token Index: 293

Text #11

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8598. Min Act: -0.1700

Data Index: 8176209 (Open Web Text)

Max Activating Token Index: 448

Text #12

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8532. Min Act: -0.1700

Data Index: 6320302 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8463. Min Act: -0.1700

Data Index: 6607803 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8473. Min Act: -0.1700

Data Index: 7427131 (Open Web Text)

Max Activating Token Index: 1004

Text #15

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8508. Min Act: -0.1700

Data Index: 4240643 (Open Web Text)

Max Activating Token Index: 920

Text #16

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8337. Min Act: -0.1700

Data Index: 7926871 (Open Web Text)

Max Activating Token Index: 239

Text #17

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.8481. Min Act: -0.1700

Data Index: 3352830 (Open Web Text)

Max Activating Token Index: 872

Text #18

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.7717. Min Act: -0.1700

Data Index: 1789379 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 4.2034. Min Range: -4.2034

Max Act: 3.7697. Min Act: -0.1700

Data Index: 4402282 (Open Web Text)

Max Activating Token Index: 442