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

Dataset: Open Web Text

Neuron 2098 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: 6.5206. Min Range: -6.5206

Max Act: 6.5206. Min Act: -0.1700

Data Index: 6990401 (Open Web Text)

Max Activating Token Index: 274

Text #1

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.4479. Min Act: -0.1700

Data Index: 134492 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.3858. Min Act: -0.1700

Data Index: 688520 (Open Web Text)

Max Activating Token Index: 883

Text #3

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.3988. Min Act: -0.1700

Data Index: 7737956 (Open Web Text)

Max Activating Token Index: 999

Text #4

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.3011. Min Act: -0.1700

Data Index: 1993560 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.3399. Min Act: -0.1700

Data Index: 3890150 (Open Web Text)

Max Activating Token Index: 513

Text #6

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.3108. Min Act: -0.1700

Data Index: 4730361 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.3210. Min Act: -0.1700

Data Index: 4683518 (Open Web Text)

Max Activating Token Index: 543

Text #8

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.2734. Min Act: -0.1700

Data Index: 5193771 (Open Web Text)

Max Activating Token Index: 304

Text #9

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.2403. Min Act: -0.1700

Data Index: 6437227 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.2626. Min Act: -0.1700

Data Index: 5590764 (Open Web Text)

Max Activating Token Index: 853

Text #11

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.1923. Min Act: -0.1700

Data Index: 4130046 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.1941. Min Act: -0.1700

Data Index: 2423006 (Open Web Text)

Max Activating Token Index: 370

Text #13

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.1736. Min Act: -0.1700

Data Index: 6630723 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.2303. Min Act: -0.1700

Data Index: 4378447 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.1968. Min Act: -0.1700

Data Index: 1530934 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.2273. Min Act: -0.1700

Data Index: 8696175 (Open Web Text)

Max Activating Token Index: 862

Text #17

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.1827. Min Act: -0.1700

Data Index: 386850 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.1438. Min Act: -0.1700

Data Index: 2478275 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 6.5206. Min Range: -6.5206

Max Act: 6.1636. Min Act: -0.1700

Data Index: 2992228 (Open Web Text)

Max Activating Token Index: 232