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

Dataset: Open Web Text

Neuron 2553 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: 3.4894. Min Range: -3.4894

Max Act: 3.4894. Min Act: -0.1700

Data Index: 7847987 (Open Web Text)

Max Activating Token Index: 255

Text #1

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.4213. Min Act: -0.1700

Data Index: 8831217 (Open Web Text)

Max Activating Token Index: 576

Text #2

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3959. Min Act: -0.1700

Data Index: 1420544 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3723. Min Act: -0.1700

Data Index: 3825161 (Open Web Text)

Max Activating Token Index: 413

Text #4

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3522. Min Act: -0.1700

Data Index: 8564564 (Open Web Text)

Max Activating Token Index: 795

Text #5

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3506. Min Act: -0.1700

Data Index: 4515325 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3382. Min Act: -0.1700

Data Index: 5276385 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3246. Min Act: -0.1700

Data Index: 8822785 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3198. Min Act: -0.1700

Data Index: 7493611 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3156. Min Act: -0.1700

Data Index: 1874213 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3059. Min Act: -0.1700

Data Index: 2411320 (Open Web Text)

Max Activating Token Index: 748

Text #11

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3151. Min Act: -0.1700

Data Index: 3923829 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3141. Min Act: -0.1700

Data Index: 3077643 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2853. Min Act: -0.1700

Data Index: 8299474 (Open Web Text)

Max Activating Token Index: 928

Text #14

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2993. Min Act: -0.1700

Data Index: 5370396 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3065. Min Act: -0.1700

Data Index: 474891 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.3018. Min Act: -0.1700

Data Index: 6427496 (Open Web Text)

Max Activating Token Index: 814

Text #17

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2818. Min Act: -0.1700

Data Index: 5327174 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2858. Min Act: -0.1700

Data Index: 207188 (Open Web Text)

Max Activating Token Index: 857

Text #19

Max Range: 3.4894. Min Range: -3.4894

Max Act: 3.2951. Min Act: -0.1700

Data Index: 3340488 (Open Web Text)

Max Activating Token Index: 554