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

Dataset: Open Web Text

Neuron 735 in Layer 6

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: 5.2206. Min Range: -5.2206

Max Act: 5.2206. Min Act: -0.1700

Data Index: 2218426 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.1739. Min Act: -0.1700

Data Index: 4618639 (Open Web Text)

Max Activating Token Index: 765

Text #2

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.1655. Min Act: -0.1700

Data Index: 5482033 (Open Web Text)

Max Activating Token Index: 286

Text #3

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0758. Min Act: -0.1700

Data Index: 2040113 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0945. Min Act: -0.1700

Data Index: 8546695 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.1180. Min Act: -0.1700

Data Index: 2110124 (Open Web Text)

Max Activating Token Index: 748

Text #6

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0281. Min Act: -0.1700

Data Index: 8702030 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0346. Min Act: -0.1700

Data Index: 3663763 (Open Web Text)

Max Activating Token Index: 867

Text #8

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0249. Min Act: -0.1700

Data Index: 6081830 (Open Web Text)

Max Activating Token Index: 143

Text #9

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0307. Min Act: -0.1700

Data Index: 1516551 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0153. Min Act: -0.1700

Data Index: 576490 (Open Web Text)

Max Activating Token Index: 661

Text #11

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0304. Min Act: -0.1700

Data Index: 7505949 (Open Web Text)

Max Activating Token Index: 867

Text #12

Max Range: 5.2206. Min Range: -5.2206

Max Act: 5.0325. Min Act: -0.1700

Data Index: 3714048 (Open Web Text)

Max Activating Token Index: 813

Text #13

Max Range: 5.2206. Min Range: -5.2206

Max Act: 4.9944. Min Act: -0.1700

Data Index: 259708 (Open Web Text)

Max Activating Token Index: 306

Text #14

Max Range: 5.2206. Min Range: -5.2206

Max Act: 4.9728. Min Act: -0.1700

Data Index: 1139408 (Open Web Text)

Max Activating Token Index: 780

Text #15

Max Range: 5.2206. Min Range: -5.2206

Max Act: 4.9762. Min Act: -0.1700

Data Index: 6070608 (Open Web Text)

Max Activating Token Index: 712

Text #16

Max Range: 5.2206. Min Range: -5.2206

Max Act: 4.9593. Min Act: -0.1700

Data Index: 7806847 (Open Web Text)

Max Activating Token Index: 838

Text #17

Max Range: 5.2206. Min Range: -5.2206

Max Act: 4.9813. Min Act: -0.1700

Data Index: 8649076 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 5.2206. Min Range: -5.2206

Max Act: 4.9224. Min Act: -0.1700

Data Index: 5046462 (Open Web Text)

Max Activating Token Index: 403

Text #19

Max Range: 5.2206. Min Range: -5.2206

Max Act: 4.9275. Min Act: -0.1700

Data Index: 246609 (Open Web Text)

Max Activating Token Index: 652