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

Dataset: Open Web Text

Neuron 1229 in Layer 4

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: 3.6552. Min Range: -3.6552

Max Act: 3.6323. Min Act: -0.1700

Data Index: 2823238 (Open Web Text)

Max Activating Token Index: 493

Text #1

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6552. Min Act: -0.1700

Data Index: 7309664 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6266. Min Act: -0.1700

Data Index: 5622247 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6130. Min Act: -0.1700

Data Index: 4898412 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6237. Min Act: -0.1700

Data Index: 6111570 (Open Web Text)

Max Activating Token Index: 297

Text #5

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.6243. Min Act: -0.1700

Data Index: 2850046 (Open Web Text)

Max Activating Token Index: 234

Text #6

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5925. Min Act: -0.1700

Data Index: 7560647 (Open Web Text)

Max Activating Token Index: 749

Text #7

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5886. Min Act: -0.1700

Data Index: 8716098 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5829. Min Act: -0.1700

Data Index: 4888408 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5851. Min Act: -0.1700

Data Index: 5559720 (Open Web Text)

Max Activating Token Index: 315

Text #10

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5622. Min Act: -0.1700

Data Index: 6389441 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5696. Min Act: -0.1700

Data Index: 7155177 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5615. Min Act: -0.1700

Data Index: 4708495 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5545. Min Act: -0.1700

Data Index: 8388951 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5449. Min Act: -0.1700

Data Index: 7348114 (Open Web Text)

Max Activating Token Index: 297

Text #15

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5538. Min Act: -0.1700

Data Index: 1477911 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5723. Min Act: -0.1700

Data Index: 2683492 (Open Web Text)

Max Activating Token Index: 362

Text #17

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5636. Min Act: -0.1700

Data Index: 2469542 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5620. Min Act: -0.1700

Data Index: 7084463 (Open Web Text)

Max Activating Token Index: 198

Text #19

Max Range: 3.6552. Min Range: -3.6552

Max Act: 3.5431. Min Act: -0.1700

Data Index: 3442992 (Open Web Text)

Max Activating Token Index: 164