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

Dataset: Open Web Text

Neuron 2996 in Layer 4

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: 3.3647. Min Range: -3.3647

Max Act: 3.3647. Min Act: -0.1700

Data Index: 1742137 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3394. Min Act: -0.1700

Data Index: 18646 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3120. Min Act: -0.1700

Data Index: 1913784 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3107. Min Act: -0.1700

Data Index: 5390743 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3150. Min Act: -0.1700

Data Index: 222949 (Open Web Text)

Max Activating Token Index: 635

Text #5

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2817. Min Act: -0.1700

Data Index: 683967 (Open Web Text)

Max Activating Token Index: 583

Text #6

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2945. Min Act: -0.1700

Data Index: 2618940 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3126. Min Act: -0.1700

Data Index: 3100926 (Open Web Text)

Max Activating Token Index: 519

Text #8

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3223. Min Act: -0.1700

Data Index: 6786007 (Open Web Text)

Max Activating Token Index: 975

Text #9

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2946. Min Act: -0.1700

Data Index: 6732496 (Open Web Text)

Max Activating Token Index: 880

Text #10

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2904. Min Act: -0.1700

Data Index: 1293677 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2815. Min Act: -0.1700

Data Index: 1027192 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2695. Min Act: -0.1700

Data Index: 4618439 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2351. Min Act: -0.1700

Data Index: 3120344 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2534. Min Act: -0.1700

Data Index: 663960 (Open Web Text)

Max Activating Token Index: 700

Text #15

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2447. Min Act: -0.1700

Data Index: 7103896 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2659. Min Act: -0.1700

Data Index: 4931259 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2519. Min Act: -0.1700

Data Index: 4530478 (Open Web Text)

Max Activating Token Index: 976

Text #18

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2647. Min Act: -0.1700

Data Index: 1754131 (Open Web Text)

Max Activating Token Index: 353

Text #19

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2611. Min Act: -0.1700

Data Index: 1254973 (Open Web Text)

Max Activating Token Index: 621