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

Dataset: Open Web Text

Neuron 1608 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: 4.2946. Min Range: -4.2946

Max Act: 4.2946. Min Act: -0.1700

Data Index: 3168535 (Open Web Text)

Max Activating Token Index: 245

Text #1

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2899. Min Act: -0.1700

Data Index: 152884 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1690. Min Act: -0.1700

Data Index: 181660 (Open Web Text)

Max Activating Token Index: 326

Text #3

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1680. Min Act: -0.1700

Data Index: 4731930 (Open Web Text)

Max Activating Token Index: 802

Text #4

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1455. Min Act: -0.1700

Data Index: 1684104 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1477. Min Act: -0.1700

Data Index: 5469264 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1448. Min Act: -0.1700

Data Index: 4543700 (Open Web Text)

Max Activating Token Index: 702

Text #7

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0621. Min Act: -0.1700

Data Index: 7319155 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0325. Min Act: -0.1700

Data Index: 8666342 (Open Web Text)

Max Activating Token Index: 571

Text #9

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0470. Min Act: -0.1700

Data Index: 5413426 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0476. Min Act: -0.1700

Data Index: 8120116 (Open Web Text)

Max Activating Token Index: 995

Text #11

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0325. Min Act: -0.1700

Data Index: 1249236 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 4.2946. Min Range: -4.2946

Max Act: 3.9860. Min Act: -0.1700

Data Index: 3777026 (Open Web Text)

Max Activating Token Index: 147

Text #13

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0002. Min Act: -0.1700

Data Index: 4537894 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.0262. Min Act: -0.1700

Data Index: 1188656 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 4.2946. Min Range: -4.2946

Max Act: 3.9833. Min Act: -0.1700

Data Index: 5619096 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 4.2946. Min Range: -4.2946

Max Act: 3.9409. Min Act: -0.1700

Data Index: 4071477 (Open Web Text)

Max Activating Token Index: 408

Text #17

Max Range: 4.2946. Min Range: -4.2946

Max Act: 3.9663. Min Act: -0.1700

Data Index: 4073423 (Open Web Text)

Max Activating Token Index: 92

Text #18

Max Range: 4.2946. Min Range: -4.2946

Max Act: 3.9665. Min Act: -0.1700

Data Index: 5912187 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 4.2946. Min Range: -4.2946

Max Act: 3.9641. Min Act: -0.1700

Data Index: 1335618 (Open Web Text)

Max Activating Token Index: 396