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

Dataset: Open Web Text

Neuron 162 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: 4.0089. Min Range: -4.0089

Max Act: 4.0089. Min Act: -0.1700

Data Index: 5793887 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.9448. Min Act: -0.1700

Data Index: 3932365 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.9469. Min Act: -0.1700

Data Index: 2341002 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.8617. Min Act: -0.1700

Data Index: 2641734 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.8330. Min Act: -0.1700

Data Index: 6200047 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.8609. Min Act: -0.1700

Data Index: 809320 (Open Web Text)

Max Activating Token Index: 938

Text #6

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.8199. Min Act: -0.1700

Data Index: 8115800 (Open Web Text)

Max Activating Token Index: 995

Text #7

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.8231. Min Act: -0.1700

Data Index: 7335495 (Open Web Text)

Max Activating Token Index: 202

Text #8

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7860. Min Act: -0.1700

Data Index: 1825636 (Open Web Text)

Max Activating Token Index: 943

Text #9

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7985. Min Act: -0.1700

Data Index: 7352420 (Open Web Text)

Max Activating Token Index: 904

Text #10

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7820. Min Act: -0.1700

Data Index: 649928 (Open Web Text)

Max Activating Token Index: 690

Text #11

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7964. Min Act: -0.1700

Data Index: 1302083 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7542. Min Act: -0.1700

Data Index: 5904878 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7489. Min Act: -0.1700

Data Index: 2802642 (Open Web Text)

Max Activating Token Index: 484

Text #14

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7428. Min Act: -0.1700

Data Index: 2525999 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7527. Min Act: -0.1700

Data Index: 942290 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7452. Min Act: -0.1700

Data Index: 3528226 (Open Web Text)

Max Activating Token Index: 486

Text #17

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7559. Min Act: -0.1700

Data Index: 1695641 (Open Web Text)

Max Activating Token Index: 324

Text #18

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1878075 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 4.0089. Min Range: -4.0089

Max Act: 3.7374. Min Act: -0.1700

Data Index: 4665697 (Open Web Text)

Max Activating Token Index: 982