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

Dataset: Open Web Text

Neuron 2685 in Layer 3

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: 3.5640. Min Range: -3.5640

Max Act: 3.5204. Min Act: -0.1700

Data Index: 3339878 (Open Web Text)

Max Activating Token Index: 617

Text #1

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5640. Min Act: -0.1700

Data Index: 1777182 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5369. Min Act: -0.1700

Data Index: 8174692 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1430937 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.5456. Min Act: -0.1700

Data Index: 6893259 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4522. Min Act: -0.1700

Data Index: 5507288 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4384. Min Act: -0.1700

Data Index: 5921168 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4464. Min Act: -0.1700

Data Index: 6394973 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4386. Min Act: -0.1700

Data Index: 4052488 (Open Web Text)

Max Activating Token Index: 924

Text #9

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4020. Min Act: -0.1700

Data Index: 1207273 (Open Web Text)

Max Activating Token Index: 359

Text #10

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3736. Min Act: -0.1700

Data Index: 7130595 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4160. Min Act: -0.1700

Data Index: 3401532 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4103. Min Act: -0.1700

Data Index: 5183747 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.4517. Min Act: -0.1700

Data Index: 5472548 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3963. Min Act: -0.1700

Data Index: 485164 (Open Web Text)

Max Activating Token Index: 873

Text #15

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3662. Min Act: -0.1700

Data Index: 643965 (Open Web Text)

Max Activating Token Index: 705

Text #16

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3988. Min Act: -0.1700

Data Index: 6424340 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3676. Min Act: -0.1700

Data Index: 1465380 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3768. Min Act: -0.1700

Data Index: 7489708 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 3.5640. Min Range: -3.5640

Max Act: 3.3925. Min Act: -0.1700

Data Index: 1112006 (Open Web Text)

Max Activating Token Index: 779