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

Dataset: Open Web Text

Neuron 2613 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: 5.6394. Min Range: -5.6394

Max Act: 5.6394. Min Act: -0.1700

Data Index: 8113911 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.4117. Min Act: -0.1700

Data Index: 1113446 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.3409. Min Act: -0.1700

Data Index: 3443217 (Open Web Text)

Max Activating Token Index: 249

Text #3

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.2922. Min Act: -0.1700

Data Index: 6269926 (Open Web Text)

Max Activating Token Index: 100

Text #4

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.1793. Min Act: -0.1700

Data Index: 6590936 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0983. Min Act: -0.1700

Data Index: 5781504 (Open Web Text)

Max Activating Token Index: 675

Text #6

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0685. Min Act: -0.1700

Data Index: 6349303 (Open Web Text)

Max Activating Token Index: 950

Text #7

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0686. Min Act: -0.1700

Data Index: 1036477 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0350. Min Act: -0.1700

Data Index: 4539288 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0789. Min Act: -0.1700

Data Index: 7090221 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 5.6394. Min Range: -5.6394

Max Act: 4.9774. Min Act: -0.1700

Data Index: 1105050 (Open Web Text)

Max Activating Token Index: 947

Text #11

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0165. Min Act: -0.1700

Data Index: 6702953 (Open Web Text)

Max Activating Token Index: 625

Text #12

Max Range: 5.6394. Min Range: -5.6394

Max Act: 4.9893. Min Act: -0.1700

Data Index: 6050250 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 5.6394. Min Range: -5.6394

Max Act: 4.9898. Min Act: -0.1700

Data Index: 1735181 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0175. Min Act: -0.1700

Data Index: 2278124 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 5.6394. Min Range: -5.6394

Max Act: 5.0190. Min Act: -0.1700

Data Index: 2158472 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 5.6394. Min Range: -5.6394

Max Act: 4.9720. Min Act: -0.1700

Data Index: 1333420 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 5.6394. Min Range: -5.6394

Max Act: 4.9987. Min Act: -0.1700

Data Index: 3577181 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 5.6394. Min Range: -5.6394

Max Act: 4.9381. Min Act: -0.1700

Data Index: 6340389 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 5.6394. Min Range: -5.6394

Max Act: 4.9433. Min Act: -0.1700

Data Index: 7853031 (Open Web Text)

Max Activating Token Index: 855