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

Dataset: Open Web Text

Neuron 249 in Layer 3

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: 4.2348. Min Range: -4.2348

Max Act: 4.2264. Min Act: -0.1700

Data Index: 202521 (Open Web Text)

Max Activating Token Index: 647

Text #1

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1932. Min Act: -0.1700

Data Index: 1375063 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.2084. Min Act: -0.1700

Data Index: 1099029 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.2348. Min Act: -0.1700

Data Index: 8827884 (Open Web Text)

Max Activating Token Index: 565

Text #4

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.2247. Min Act: -0.1700

Data Index: 4565629 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1703. Min Act: -0.1700

Data Index: 7209407 (Open Web Text)

Max Activating Token Index: 898

Text #6

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1712. Min Act: -0.1700

Data Index: 5088326 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1985. Min Act: -0.1700

Data Index: 7526306 (Open Web Text)

Max Activating Token Index: 525

Text #8

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1425. Min Act: -0.1700

Data Index: 3108089 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1669. Min Act: -0.1700

Data Index: 5508671 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1287. Min Act: -0.1700

Data Index: 7070828 (Open Web Text)

Max Activating Token Index: 1006

Text #11

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1722. Min Act: -0.1700

Data Index: 7428394 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1138. Min Act: -0.1700

Data Index: 4238586 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.0968. Min Act: -0.1700

Data Index: 3308790 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1155. Min Act: -0.1700

Data Index: 3204148 (Open Web Text)

Max Activating Token Index: 985

Text #15

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1146. Min Act: -0.1700

Data Index: 5303997 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1369. Min Act: -0.1700

Data Index: 922593 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1630. Min Act: -0.1700

Data Index: 3441589 (Open Web Text)

Max Activating Token Index: 608

Text #18

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1258. Min Act: -0.1700

Data Index: 6899381 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 4.2348. Min Range: -4.2348

Max Act: 4.1098. Min Act: -0.1700

Data Index: 4983816 (Open Web Text)

Max Activating Token Index: 97