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

Dataset: Open Web Text

Neuron 2228 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: 4.5868. Min Range: -4.5868

Max Act: 4.5868. Min Act: -0.1700

Data Index: 471237 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.4678. Min Act: -0.1700

Data Index: 2212826 (Open Web Text)

Max Activating Token Index: 730

Text #2

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.4479. Min Act: -0.1700

Data Index: 7110576 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.4049. Min Act: -0.1700

Data Index: 4806884 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.4309. Min Act: -0.1700

Data Index: 3336726 (Open Web Text)

Max Activating Token Index: 785

Text #5

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3895. Min Act: -0.1700

Data Index: 8293367 (Open Web Text)

Max Activating Token Index: 482

Text #6

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3962. Min Act: -0.1700

Data Index: 8389948 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3665. Min Act: -0.1700

Data Index: 4699743 (Open Web Text)

Max Activating Token Index: 386

Text #8

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3704. Min Act: -0.1700

Data Index: 6904468 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3585. Min Act: -0.1700

Data Index: 2929572 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3595. Min Act: -0.1700

Data Index: 6980160 (Open Web Text)

Max Activating Token Index: 922

Text #11

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3101. Min Act: -0.1700

Data Index: 1444717 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.2885. Min Act: -0.1700

Data Index: 5158246 (Open Web Text)

Max Activating Token Index: 119

Text #13

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.3104. Min Act: -0.1700

Data Index: 5105055 (Open Web Text)

Max Activating Token Index: 257

Text #14

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.2605. Min Act: -0.1700

Data Index: 4705334 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.2860. Min Act: -0.1700

Data Index: 3233638 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.2948. Min Act: -0.1700

Data Index: 1097701 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.2635. Min Act: -0.1700

Data Index: 5339587 (Open Web Text)

Max Activating Token Index: 861

Text #18

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.2801. Min Act: -0.1700

Data Index: 933848 (Open Web Text)

Max Activating Token Index: 986

Text #19

Max Range: 4.5868. Min Range: -4.5868

Max Act: 4.2456. Min Act: -0.1700

Data Index: 3781283 (Open Web Text)

Max Activating Token Index: 221