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

Dataset: Open Web Text

Neuron 562 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: 6.2946. Min Range: -6.2946

Max Act: 6.2946. Min Act: -0.1700

Data Index: 1529339 (Open Web Text)

Max Activating Token Index: 524

Text #1

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.2313. Min Act: -0.1700

Data Index: 6385657 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.2550. Min Act: -0.1700

Data Index: 304169 (Open Web Text)

Max Activating Token Index: 712

Text #3

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.2146. Min Act: -0.1700

Data Index: 1867464 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.2253. Min Act: -0.1700

Data Index: 2264536 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.1431. Min Act: -0.1700

Data Index: 5018380 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.1271. Min Act: -0.1700

Data Index: 2740485 (Open Web Text)

Max Activating Token Index: 991

Text #7

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.1323. Min Act: -0.1700

Data Index: 6509445 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.1146. Min Act: -0.1700

Data Index: 1703320 (Open Web Text)

Max Activating Token Index: 964

Text #9

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0778. Min Act: -0.1700

Data Index: 5796084 (Open Web Text)

Max Activating Token Index: 155

Text #10

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.1466. Min Act: -0.1700

Data Index: 3757961 (Open Web Text)

Max Activating Token Index: 697

Text #11

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0662. Min Act: -0.1700

Data Index: 2084419 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0433. Min Act: -0.1700

Data Index: 4029178 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0705. Min Act: -0.1700

Data Index: 45723 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0514. Min Act: -0.1700

Data Index: 5098138 (Open Web Text)

Max Activating Token Index: 707

Text #15

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0666. Min Act: -0.1700

Data Index: 2374920 (Open Web Text)

Max Activating Token Index: 799

Text #16

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0398. Min Act: -0.1700

Data Index: 3175129 (Open Web Text)

Max Activating Token Index: 879

Text #17

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0704. Min Act: -0.1700

Data Index: 5410813 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0336. Min Act: -0.1700

Data Index: 1302002 (Open Web Text)

Max Activating Token Index: 908

Text #19

Max Range: 6.2946. Min Range: -6.2946

Max Act: 6.0039. Min Act: -0.1700

Data Index: 703567 (Open Web Text)

Max Activating Token Index: 376