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

Dataset: Open Web Text

Neuron 2837 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: 3.5263. Min Range: -3.5263

Max Act: 3.5263. Min Act: -0.1700

Data Index: 6986007 (Open Web Text)

Max Activating Token Index: 795

Text #1

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4697. Min Act: -0.1700

Data Index: 7083645 (Open Web Text)

Max Activating Token Index: 223

Text #2

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4946. Min Act: -0.1700

Data Index: 4753911 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4911. Min Act: -0.1700

Data Index: 7176393 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4694. Min Act: -0.1700

Data Index: 6187350 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4891. Min Act: -0.1700

Data Index: 5744038 (Open Web Text)

Max Activating Token Index: 969

Text #6

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4461. Min Act: -0.1700

Data Index: 7087969 (Open Web Text)

Max Activating Token Index: 95

Text #7

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4151. Min Act: -0.1700

Data Index: 6379090 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4475. Min Act: -0.1700

Data Index: 5380635 (Open Web Text)

Max Activating Token Index: 794

Text #9

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4342. Min Act: -0.1700

Data Index: 7198638 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4490. Min Act: -0.1700

Data Index: 7620312 (Open Web Text)

Max Activating Token Index: 841

Text #11

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.3957. Min Act: -0.1700

Data Index: 8760201 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.3963. Min Act: -0.1700

Data Index: 3855217 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.3840. Min Act: -0.1700

Data Index: 8440236 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4099. Min Act: -0.1700

Data Index: 5185503 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.4141. Min Act: -0.1700

Data Index: 3788883 (Open Web Text)

Max Activating Token Index: 412

Text #16

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.3963. Min Act: -0.1700

Data Index: 1582343 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.3671. Min Act: -0.1700

Data Index: 6559454 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.3632. Min Act: -0.1700

Data Index: 6750547 (Open Web Text)

Max Activating Token Index: 361

Text #19

Max Range: 3.5263. Min Range: -3.5263

Max Act: 3.3897. Min Act: -0.1700

Data Index: 4302501 (Open Web Text)

Max Activating Token Index: 536