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

Dataset: Open Web Text

Neuron 1558 in Layer 1

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: 3.1671. Min Range: -3.1671

Max Act: 3.1671. Min Act: -0.1675

Data Index: 4515526 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.5885. Min Act: -0.1684

Data Index: 6143080 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.5599. Min Act: -0.0190

Data Index: 3724017 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.4450. Min Act: -0.1695

Data Index: 2927137 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3837. Min Act: -0.1513

Data Index: 425427 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3603. Min Act: -0.1687

Data Index: 4834047 (Open Web Text)

Max Activating Token Index: 933

Text #6

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3750. Min Act: -0.1265

Data Index: 1796343 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3659. Min Act: -0.0548

Data Index: 6143062 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.4012. Min Act: -0.1691

Data Index: 6143067 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3396. Min Act: -0.1655

Data Index: 6329622 (Open Web Text)

Max Activating Token Index: 201

Text #10

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3306. Min Act: -0.1696

Data Index: 4515521 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3383. Min Act: -0.0611

Data Index: 6226755 (Open Web Text)

Max Activating Token Index: 265

Text #12

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3378. Min Act: -0.1699

Data Index: 6143079 (Open Web Text)

Max Activating Token Index: 195

Text #13

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3169. Min Act: 0.1490

Data Index: 4229997 (Open Web Text)

Max Activating Token Index: 208

Text #14

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3285. Min Act: -0.1537

Data Index: 8557053 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3238. Min Act: 0.0777

Data Index: 8162051 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3271. Min Act: 0.0596

Data Index: 4515536 (Open Web Text)

Max Activating Token Index: 315

Text #17

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3070. Min Act: -0.1699

Data Index: 6143053 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.2997. Min Act: -0.1690

Data Index: 3585495 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 3.1671. Min Range: -3.1671

Max Act: 2.3149. Min Act: -0.1700

Data Index: 5599954 (Open Web Text)

Max Activating Token Index: 584