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

Dataset: Open Web Text

Neuron 506 in Layer 6

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: 4.6488. Min Range: -4.6488

Max Act: 4.6488. Min Act: -0.1700

Data Index: 4467943 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5461. Min Act: -0.1700

Data Index: 6311218 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5189. Min Act: -0.1700

Data Index: 1687415 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.5282. Min Act: -0.1700

Data Index: 7334611 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.4889. Min Act: -0.1700

Data Index: 5645156 (Open Web Text)

Max Activating Token Index: 267

Text #5

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.4382. Min Act: -0.1700

Data Index: 7648367 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3857. Min Act: -0.1700

Data Index: 3255239 (Open Web Text)

Max Activating Token Index: 841

Text #7

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.4337. Min Act: -0.1700

Data Index: 8473884 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.4349. Min Act: -0.1700

Data Index: 4294143 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3690. Min Act: -0.1700

Data Index: 3060586 (Open Web Text)

Max Activating Token Index: 305

Text #10

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3551. Min Act: -0.1700

Data Index: 1680075 (Open Web Text)

Max Activating Token Index: 439

Text #11

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3442. Min Act: -0.1700

Data Index: 840052 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3489. Min Act: -0.1700

Data Index: 2442843 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3230. Min Act: -0.1700

Data Index: 8142325 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.2992. Min Act: -0.1700

Data Index: 1341880 (Open Web Text)

Max Activating Token Index: 108

Text #15

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3342. Min Act: -0.1700

Data Index: 3536771 (Open Web Text)

Max Activating Token Index: 336

Text #16

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.3107. Min Act: -0.1700

Data Index: 1057720 (Open Web Text)

Max Activating Token Index: 342

Text #17

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.2731. Min Act: -0.1700

Data Index: 5954938 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.1979. Min Act: -0.1700

Data Index: 3086645 (Open Web Text)

Max Activating Token Index: 682

Text #19

Max Range: 4.6488. Min Range: -4.6488

Max Act: 4.2544. Min Act: -0.1700

Data Index: 3202978 (Open Web Text)

Max Activating Token Index: 288