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

Dataset: Open Web Text

Neuron 705 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: 4.0527. Min Range: -4.0527

Max Act: 4.0527. Min Act: -0.1700

Data Index: 1016209 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 4.0527. Min Range: -4.0527

Max Act: 4.0240. Min Act: -0.1700

Data Index: 8568993 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 4.0527. Min Range: -4.0527

Max Act: 4.0342. Min Act: -0.1700

Data Index: 2352049 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9126. Min Act: -0.1700

Data Index: 161640 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 4.0527. Min Range: -4.0527

Max Act: 4.0056. Min Act: -0.1700

Data Index: 1527709 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 4.0527. Min Range: -4.0527

Max Act: 4.0189. Min Act: -0.1700

Data Index: 4683611 (Open Web Text)

Max Activating Token Index: 546

Text #6

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9868. Min Act: -0.1700

Data Index: 5088032 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9965. Min Act: -0.1700

Data Index: 3687944 (Open Web Text)

Max Activating Token Index: 129

Text #8

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9909. Min Act: -0.1700

Data Index: 3314065 (Open Web Text)

Max Activating Token Index: 155

Text #9

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9620. Min Act: -0.1700

Data Index: 8625877 (Open Web Text)

Max Activating Token Index: 549

Text #10

Max Range: 4.0527. Min Range: -4.0527

Max Act: 4.0186. Min Act: -0.1700

Data Index: 1617806 (Open Web Text)

Max Activating Token Index: 501

Text #11

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9566. Min Act: -0.1700

Data Index: 3994251 (Open Web Text)

Max Activating Token Index: 376

Text #12

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9418. Min Act: -0.1700

Data Index: 3687941 (Open Web Text)

Max Activating Token Index: 426

Text #13

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9674. Min Act: -0.1700

Data Index: 3687950 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9130. Min Act: -0.1700

Data Index: 1065542 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9085. Min Act: -0.1700

Data Index: 3116097 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9395. Min Act: -0.1700

Data Index: 5394249 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9090. Min Act: -0.1700

Data Index: 2810335 (Open Web Text)

Max Activating Token Index: 38

Text #18

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.8946. Min Act: -0.1700

Data Index: 469041 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 4.0527. Min Range: -4.0527

Max Act: 3.9134. Min Act: -0.1700

Data Index: 5194844 (Open Web Text)

Max Activating Token Index: 412