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

Dataset: Open Web Text

Neuron 781 in Layer 2

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: 6.4871. Min Range: -6.4871

Max Act: 6.4871. Min Act: -0.1700

Data Index: 5323541 (Open Web Text)

Max Activating Token Index: 207

Text #1

Max Range: 6.4871. Min Range: -6.4871

Max Act: 6.0148. Min Act: -0.1700

Data Index: 3841337 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 6.4871. Min Range: -6.4871

Max Act: 6.0974. Min Act: -0.1700

Data Index: 342104 (Open Web Text)

Max Activating Token Index: 713

Text #3

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.9816. Min Act: -0.1700

Data Index: 619755 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 6.4871. Min Range: -6.4871

Max Act: 6.0137. Min Act: -0.1700

Data Index: 224520 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 6.4871. Min Range: -6.4871

Max Act: 6.0195. Min Act: -0.1700

Data Index: 3748993 (Open Web Text)

Max Activating Token Index: 591

Text #6

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.9850. Min Act: -0.1700

Data Index: 4316758 (Open Web Text)

Max Activating Token Index: 206

Text #7

Max Range: 6.4871. Min Range: -6.4871

Max Act: 6.0054. Min Act: -0.1700

Data Index: 5651121 (Open Web Text)

Max Activating Token Index: 698

Text #8

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.9416. Min Act: -0.1700

Data Index: 3582427 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.9586. Min Act: -0.1700

Data Index: 3517267 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 6.4871. Min Range: -6.4871

Max Act: 6.0061. Min Act: -0.1700

Data Index: 7200848 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.9408. Min Act: -0.1700

Data Index: 5945069 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.8826. Min Act: -0.1700

Data Index: 2186409 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.8965. Min Act: -0.1700

Data Index: 5798867 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.8751. Min Act: -0.1700

Data Index: 725311 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.7936. Min Act: -0.1700

Data Index: 2200452 (Open Web Text)

Max Activating Token Index: 943

Text #16

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.7791. Min Act: -0.1700

Data Index: 5540765 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.7109. Min Act: -0.1700

Data Index: 4462541 (Open Web Text)

Max Activating Token Index: 525

Text #18

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.7175. Min Act: -0.1700

Data Index: 1302721 (Open Web Text)

Max Activating Token Index: 616

Text #19

Max Range: 6.4871. Min Range: -6.4871

Max Act: 5.7310. Min Act: -0.1700

Data Index: 8336806 (Open Web Text)

Max Activating Token Index: 477