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

Dataset: Open Web Text

Neuron 2499 in Layer 3

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: 4.2048. Min Range: -4.2048

Max Act: 4.2048. Min Act: -0.1700

Data Index: 6425098 (Open Web Text)

Max Activating Token Index: 86

Text #1

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.1634. Min Act: -0.1700

Data Index: 8829569 (Open Web Text)

Max Activating Token Index: 1001

Text #2

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0444. Min Act: -0.1700

Data Index: 2143930 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0837. Min Act: -0.1700

Data Index: 3997982 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0921. Min Act: -0.1700

Data Index: 2895548 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0292. Min Act: -0.1700

Data Index: 1575167 (Open Web Text)

Max Activating Token Index: 938

Text #6

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0417. Min Act: -0.1700

Data Index: 3267500 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0516. Min Act: -0.1700

Data Index: 6251873 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0237. Min Act: -0.1700

Data Index: 600322 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0153. Min Act: -0.1700

Data Index: 311825 (Open Web Text)

Max Activating Token Index: 137

Text #10

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0374. Min Act: -0.1700

Data Index: 2355644 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0148. Min Act: -0.1700

Data Index: 8701451 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 4.2048. Min Range: -4.2048

Max Act: 3.9921. Min Act: -0.1700

Data Index: 4660147 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 4.2048. Min Range: -4.2048

Max Act: 3.9986. Min Act: -0.1700

Data Index: 6621283 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 4.2048. Min Range: -4.2048

Max Act: 3.9881. Min Act: -0.1700

Data Index: 2268419 (Open Web Text)

Max Activating Token Index: 469

Text #15

Max Range: 4.2048. Min Range: -4.2048

Max Act: 4.0396. Min Act: -0.1700

Data Index: 4148877 (Open Web Text)

Max Activating Token Index: 562

Text #16

Max Range: 4.2048. Min Range: -4.2048

Max Act: 3.9809. Min Act: -0.1700

Data Index: 3114693 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 4.2048. Min Range: -4.2048

Max Act: 3.9450. Min Act: -0.1700

Data Index: 6883924 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 4.2048. Min Range: -4.2048

Max Act: 3.9864. Min Act: -0.1700

Data Index: 7041984 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 4.2048. Min Range: -4.2048

Max Act: 3.9757. Min Act: -0.1700

Data Index: 3903497 (Open Web Text)

Max Activating Token Index: 751