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

Dataset: Open Web Text

Neuron 3045 in Layer 2

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: 1.7348. Min Range: -1.7348

Max Act: 1.7348. Min Act: -0.1700

Data Index: 7433770 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.7019. Min Act: -0.1700

Data Index: 3676991 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6972. Min Act: -0.1700

Data Index: 7523102 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.7043. Min Act: -0.1699

Data Index: 8172999 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6990. Min Act: -0.1700

Data Index: 8781314 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6902. Min Act: -0.1700

Data Index: 5234560 (Open Web Text)

Max Activating Token Index: 792

Text #6

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6813. Min Act: -0.1687

Data Index: 4401254 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6652. Min Act: -0.1700

Data Index: 4826408 (Open Web Text)

Max Activating Token Index: 254

Text #8

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6689. Min Act: -0.1700

Data Index: 8751240 (Open Web Text)

Max Activating Token Index: 717

Text #9

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6602. Min Act: -0.1700

Data Index: 5891972 (Open Web Text)

Max Activating Token Index: 337

Text #10

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6663. Min Act: -0.1700

Data Index: 6600104 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6629. Min Act: -0.1700

Data Index: 6999929 (Open Web Text)

Max Activating Token Index: 530

Text #12

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6386. Min Act: -0.1700

Data Index: 123974 (Open Web Text)

Max Activating Token Index: 266

Text #13

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6528. Min Act: -0.1667

Data Index: 1251430 (Open Web Text)

Max Activating Token Index: 327

Text #14

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6227. Min Act: -0.1699

Data Index: 7742024 (Open Web Text)

Max Activating Token Index: 1015

Text #15

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6482. Min Act: -0.1699

Data Index: 8135509 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6482. Min Act: -0.1700

Data Index: 4944244 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6354. Min Act: -0.1700

Data Index: 7367140 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6386. Min Act: -0.1699

Data Index: 3339950 (Open Web Text)

Max Activating Token Index: 111

Text #19

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.6269. Min Act: -0.1700

Data Index: 7148343 (Open Web Text)

Max Activating Token Index: 528