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

Dataset: Open Web Text

Neuron 2864 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: 2.9270. Min Range: -2.9270

Max Act: 2.9270. Min Act: -0.1700

Data Index: 3938355 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.8596. Min Act: -0.1700

Data Index: 2235151 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.8288. Min Act: -0.1700

Data Index: 3797824 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7785. Min Act: -0.1700

Data Index: 8413448 (Open Web Text)

Max Activating Token Index: 62

Text #4

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7780. Min Act: -0.1700

Data Index: 1861707 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7781. Min Act: -0.1700

Data Index: 7027743 (Open Web Text)

Max Activating Token Index: 883

Text #6

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7678. Min Act: -0.1700

Data Index: 2848410 (Open Web Text)

Max Activating Token Index: 891

Text #7

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7635. Min Act: -0.1700

Data Index: 2256639 (Open Web Text)

Max Activating Token Index: 647

Text #8

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7592. Min Act: -0.1700

Data Index: 3470172 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7629. Min Act: -0.1700

Data Index: 8540380 (Open Web Text)

Max Activating Token Index: 840

Text #10

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7505. Min Act: -0.1700

Data Index: 8595905 (Open Web Text)

Max Activating Token Index: 817

Text #11

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7798. Min Act: -0.1700

Data Index: 1421946 (Open Web Text)

Max Activating Token Index: 982

Text #12

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7447. Min Act: -0.1700

Data Index: 5185545 (Open Web Text)

Max Activating Token Index: 799

Text #13

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7515. Min Act: -0.1700

Data Index: 7506110 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7301. Min Act: -0.1700

Data Index: 6809495 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7439. Min Act: -0.1700

Data Index: 509759 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7387. Min Act: -0.1700

Data Index: 8504585 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7326. Min Act: -0.1700

Data Index: 2951979 (Open Web Text)

Max Activating Token Index: 699

Text #18

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7194. Min Act: -0.1700

Data Index: 4563459 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.9270. Min Range: -2.9270

Max Act: 2.7101. Min Act: -0.1700

Data Index: 5685810 (Open Web Text)

Max Activating Token Index: 250