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

Dataset: Open Web Text

Neuron 1722 in Layer 1

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: 1.3567. Min Range: -1.3567

Max Act: 1.3567. Min Act: -0.1698

Data Index: 8590971 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3252. Min Act: -0.1700

Data Index: 1713679 (Open Web Text)

Max Activating Token Index: 852

Text #2

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3168. Min Act: -0.1700

Data Index: 2330838 (Open Web Text)

Max Activating Token Index: 220

Text #3

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3274. Min Act: -0.1697

Data Index: 5704696 (Open Web Text)

Max Activating Token Index: 460

Text #4

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3234. Min Act: -0.1699

Data Index: 5546673 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3162. Min Act: -0.1696

Data Index: 4770544 (Open Web Text)

Max Activating Token Index: 705

Text #6

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3123. Min Act: -0.1700

Data Index: 445877 (Open Web Text)

Max Activating Token Index: 1014

Text #7

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3059. Min Act: -0.1700

Data Index: 609740 (Open Web Text)

Max Activating Token Index: 377

Text #8

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2984. Min Act: -0.1700

Data Index: 2774580 (Open Web Text)

Max Activating Token Index: 435

Text #9

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2964. Min Act: -0.1700

Data Index: 8712423 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3017. Min Act: -0.1700

Data Index: 6500392 (Open Web Text)

Max Activating Token Index: 629

Text #11

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.3000. Min Act: -0.1700

Data Index: 6319891 (Open Web Text)

Max Activating Token Index: 651

Text #12

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2945. Min Act: -0.1700

Data Index: 1001702 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2890. Min Act: -0.1700

Data Index: 381273 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2996. Min Act: -0.1700

Data Index: 8792425 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2932. Min Act: -0.1700

Data Index: 6132566 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2852. Min Act: -0.1700

Data Index: 5748931 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2837. Min Act: -0.1700

Data Index: 3144636 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2807. Min Act: -0.1697

Data Index: 5351175 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 1.3567. Min Range: -1.3567

Max Act: 1.2889. Min Act: -0.1700

Data Index: 3531868 (Open Web Text)

Max Activating Token Index: 178