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

Dataset: Open Web Text

Neuron 49 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: 5.5778. Min Range: -5.5778

Max Act: 5.5778. Min Act: -0.1700

Data Index: 1166073 (Open Web Text)

Max Activating Token Index: 58

Text #1

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4845. Min Act: -0.1700

Data Index: 70748 (Open Web Text)

Max Activating Token Index: 533

Text #2

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4711. Min Act: -0.1700

Data Index: 1329843 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4576. Min Act: -0.1700

Data Index: 8473323 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4209. Min Act: -0.1700

Data Index: 7824045 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4418. Min Act: -0.1700

Data Index: 648881 (Open Web Text)

Max Activating Token Index: 309

Text #6

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4739. Min Act: -0.1700

Data Index: 5199851 (Open Web Text)

Max Activating Token Index: 142

Text #7

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4532. Min Act: -0.1700

Data Index: 2188112 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.3913. Min Act: -0.1700

Data Index: 1501366 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4169. Min Act: -0.1700

Data Index: 282474 (Open Web Text)

Max Activating Token Index: 603

Text #10

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4020. Min Act: -0.1700

Data Index: 70750 (Open Web Text)

Max Activating Token Index: 188

Text #11

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4015. Min Act: -0.1700

Data Index: 4541498 (Open Web Text)

Max Activating Token Index: 110

Text #12

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4077. Min Act: -0.1700

Data Index: 7165775 (Open Web Text)

Max Activating Token Index: 608

Text #13

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.3885. Min Act: -0.1700

Data Index: 3090902 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.4011. Min Act: -0.1700

Data Index: 8104392 (Open Web Text)

Max Activating Token Index: 846

Text #15

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.3423. Min Act: -0.1700

Data Index: 171444 (Open Web Text)

Max Activating Token Index: 526

Text #16

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.3496. Min Act: -0.1700

Data Index: 70749 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.3834. Min Act: -0.1700

Data Index: 5427323 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.3453. Min Act: -0.1700

Data Index: 3443637 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 5.5778. Min Range: -5.5778

Max Act: 5.3821. Min Act: -0.1700

Data Index: 3873549 (Open Web Text)

Max Activating Token Index: 322