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

Dataset: Open Web Text

Neuron 850 in Layer 5

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: 3.6694. Min Range: -3.6694

Max Act: 3.6694. Min Act: -0.1700

Data Index: 2962083 (Open Web Text)

Max Activating Token Index: 281

Text #1

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.6368. Min Act: -0.1700

Data Index: 2619072 (Open Web Text)

Max Activating Token Index: 245

Text #2

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5594. Min Act: -0.1700

Data Index: 1630509 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5459. Min Act: -0.1700

Data Index: 268173 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5087. Min Act: -0.1700

Data Index: 5766091 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4779. Min Act: -0.1700

Data Index: 4355900 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4818. Min Act: -0.1700

Data Index: 1460636 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4501. Min Act: -0.1700

Data Index: 4939436 (Open Web Text)

Max Activating Token Index: 259

Text #8

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4751. Min Act: -0.1700

Data Index: 1282670 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4509. Min Act: -0.1700

Data Index: 3329654 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4733. Min Act: -0.1700

Data Index: 4860183 (Open Web Text)

Max Activating Token Index: 938

Text #11

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4447. Min Act: -0.1700

Data Index: 4899113 (Open Web Text)

Max Activating Token Index: 390

Text #12

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4543. Min Act: -0.1700

Data Index: 5604520 (Open Web Text)

Max Activating Token Index: 724

Text #13

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4277. Min Act: -0.1700

Data Index: 5802941 (Open Web Text)

Max Activating Token Index: 574

Text #14

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4269. Min Act: -0.1700

Data Index: 6207316 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4439. Min Act: -0.1700

Data Index: 7735158 (Open Web Text)

Max Activating Token Index: 731

Text #16

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4064. Min Act: -0.1700

Data Index: 167296 (Open Web Text)

Max Activating Token Index: 750

Text #17

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4098. Min Act: -0.1700

Data Index: 2932549 (Open Web Text)

Max Activating Token Index: 877

Text #18

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4120. Min Act: -0.1700

Data Index: 2630646 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3931. Min Act: -0.1700

Data Index: 3613564 (Open Web Text)

Max Activating Token Index: 108