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

Dataset: Open Web Text

Neuron 836 in Layer 4

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: 4.4208. Min Range: -4.4208

Max Act: 4.4208. Min Act: -0.1699

Data Index: 3332733 (Open Web Text)

Max Activating Token Index: 247

Text #1

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.2755. Min Act: -0.1700

Data Index: 3869025 (Open Web Text)

Max Activating Token Index: 113

Text #2

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.2568. Min Act: -0.1700

Data Index: 6328399 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.2029. Min Act: -0.1700

Data Index: 1032603 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.2200. Min Act: -0.1700

Data Index: 3051680 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.2335. Min Act: -0.1700

Data Index: 699761 (Open Web Text)

Max Activating Token Index: 138

Text #6

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.0857. Min Act: -0.1700

Data Index: 453000 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.1277. Min Act: -0.1700

Data Index: 7359797 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.1047. Min Act: -0.1700

Data Index: 6441088 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.1185. Min Act: -0.1700

Data Index: 4918612 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.0051. Min Act: -0.1700

Data Index: 5528115 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.0371. Min Act: -0.1700

Data Index: 4874174 (Open Web Text)

Max Activating Token Index: 699

Text #12

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.0121. Min Act: -0.1700

Data Index: 6784858 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 4.4208. Min Range: -4.4208

Max Act: 3.9583. Min Act: -0.1700

Data Index: 1215230 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 4.4208. Min Range: -4.4208

Max Act: 3.9850. Min Act: -0.1700

Data Index: 7739420 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 4.4208. Min Range: -4.4208

Max Act: 3.9772. Min Act: -0.1700

Data Index: 1678742 (Open Web Text)

Max Activating Token Index: 681

Text #16

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.0241. Min Act: -0.1700

Data Index: 7117111 (Open Web Text)

Max Activating Token Index: 981

Text #17

Max Range: 4.4208. Min Range: -4.4208

Max Act: 4.0065. Min Act: -0.1700

Data Index: 23091 (Open Web Text)

Max Activating Token Index: 645

Text #18

Max Range: 4.4208. Min Range: -4.4208

Max Act: 3.9361. Min Act: -0.1700

Data Index: 5127612 (Open Web Text)

Max Activating Token Index: 338

Text #19

Max Range: 4.4208. Min Range: -4.4208

Max Act: 3.9310. Min Act: -0.1700

Data Index: 3496027 (Open Web Text)

Max Activating Token Index: 287