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

Dataset: Open Web Text

Neuron 1663 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: 3.6006. Min Range: -3.6006

Max Act: 3.6006. Min Act: -0.1700

Data Index: 188085 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.5664. Min Act: -0.1700

Data Index: 5860019 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.5780. Min Act: -0.1700

Data Index: 144937 (Open Web Text)

Max Activating Token Index: 655

Text #3

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.4751. Min Act: -0.1700

Data Index: 1859726 (Open Web Text)

Max Activating Token Index: 852

Text #4

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.4969. Min Act: -0.1700

Data Index: 8126339 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.5022. Min Act: -0.1700

Data Index: 4991595 (Open Web Text)

Max Activating Token Index: 835

Text #6

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.4209. Min Act: -0.1700

Data Index: 668265 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.4095. Min Act: -0.1700

Data Index: 3630122 (Open Web Text)

Max Activating Token Index: 159

Text #8

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3866. Min Act: -0.1700

Data Index: 7240700 (Open Web Text)

Max Activating Token Index: 211

Text #9

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3685. Min Act: -0.1700

Data Index: 5586314 (Open Web Text)

Max Activating Token Index: 211

Text #10

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3842. Min Act: -0.1700

Data Index: 925031 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3575. Min Act: -0.1700

Data Index: 8147562 (Open Web Text)

Max Activating Token Index: 526

Text #12

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3517. Min Act: -0.1700

Data Index: 3699818 (Open Web Text)

Max Activating Token Index: 752

Text #13

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3372. Min Act: -0.1700

Data Index: 7492964 (Open Web Text)

Max Activating Token Index: 644

Text #14

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3614. Min Act: -0.1700

Data Index: 1968823 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3683. Min Act: -0.1700

Data Index: 2274561 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3814. Min Act: -0.1698

Data Index: 4598001 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3418. Min Act: -0.1700

Data Index: 107576 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3233. Min Act: -0.1700

Data Index: 2144100 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 3.6006. Min Range: -3.6006

Max Act: 3.3228. Min Act: -0.1700

Data Index: 8747641 (Open Web Text)

Max Activating Token Index: 969