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

Dataset: Open Web Text

Neuron 1874 in Layer 5

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: 4.0235. Min Range: -4.0235

Max Act: 4.0235. Min Act: -0.1700

Data Index: 3472668 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9020. Min Act: -0.1700

Data Index: 3208956 (Open Web Text)

Max Activating Token Index: 891

Text #2

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9232. Min Act: -0.1700

Data Index: 8678554 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8512. Min Act: -0.1700

Data Index: 6033619 (Open Web Text)

Max Activating Token Index: 268

Text #4

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8793. Min Act: -0.1700

Data Index: 4621606 (Open Web Text)

Max Activating Token Index: 562

Text #5

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8375. Min Act: -0.1700

Data Index: 8737027 (Open Web Text)

Max Activating Token Index: 276

Text #6

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8684. Min Act: -0.1700

Data Index: 8816624 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8166. Min Act: -0.1700

Data Index: 5994449 (Open Web Text)

Max Activating Token Index: 68

Text #8

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8369. Min Act: -0.1700

Data Index: 7484881 (Open Web Text)

Max Activating Token Index: 253

Text #9

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8504. Min Act: -0.1700

Data Index: 6970353 (Open Web Text)

Max Activating Token Index: 722

Text #10

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8356. Min Act: -0.1700

Data Index: 6711927 (Open Web Text)

Max Activating Token Index: 492

Text #11

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8245. Min Act: -0.1700

Data Index: 2620623 (Open Web Text)

Max Activating Token Index: 278

Text #12

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8362. Min Act: -0.1700

Data Index: 3740811 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8347. Min Act: -0.1700

Data Index: 6301168 (Open Web Text)

Max Activating Token Index: 967

Text #14

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7916. Min Act: -0.1700

Data Index: 3564486 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7942. Min Act: -0.1700

Data Index: 2999575 (Open Web Text)

Max Activating Token Index: 811

Text #16

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7920. Min Act: -0.1700

Data Index: 5498111 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7787. Min Act: -0.1700

Data Index: 2629070 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7700. Min Act: -0.1700

Data Index: 3356003 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7557. Min Act: -0.1700

Data Index: 5373013 (Open Web Text)

Max Activating Token Index: 669