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

Dataset: Open Web Text

Neuron 1824 in Layer 2

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: 1.8169. Min Range: -1.8169

Max Act: 1.8169. Min Act: -0.1700

Data Index: 5041084 (Open Web Text)

Max Activating Token Index: 489

Text #1

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7992. Min Act: -0.1700

Data Index: 3488291 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7884. Min Act: -0.1699

Data Index: 788016 (Open Web Text)

Max Activating Token Index: 273

Text #3

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7789. Min Act: -0.1700

Data Index: 5872596 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7717. Min Act: -0.1700

Data Index: 1997907 (Open Web Text)

Max Activating Token Index: 737

Text #5

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7603. Min Act: -0.1700

Data Index: 7564125 (Open Web Text)

Max Activating Token Index: 770

Text #6

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7529. Min Act: -0.1700

Data Index: 5081285 (Open Web Text)

Max Activating Token Index: 470

Text #7

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7469. Min Act: -0.1700

Data Index: 2708235 (Open Web Text)

Max Activating Token Index: 923

Text #8

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7540. Min Act: -0.1700

Data Index: 6047511 (Open Web Text)

Max Activating Token Index: 370

Text #9

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7292. Min Act: -0.1700

Data Index: 3130857 (Open Web Text)

Max Activating Token Index: 421

Text #10

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7431. Min Act: -0.1700

Data Index: 8787412 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7407. Min Act: -0.1700

Data Index: 255035 (Open Web Text)

Max Activating Token Index: 241

Text #12

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7373. Min Act: -0.1700

Data Index: 6740181 (Open Web Text)

Max Activating Token Index: 520

Text #13

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7305. Min Act: -0.1700

Data Index: 2177404 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7203. Min Act: -0.1700

Data Index: 7637290 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7192. Min Act: -0.1700

Data Index: 5824592 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7162. Min Act: -0.1700

Data Index: 4085083 (Open Web Text)

Max Activating Token Index: 404

Text #17

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7046. Min Act: -0.1700

Data Index: 3074110 (Open Web Text)

Max Activating Token Index: 606

Text #18

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7195. Min Act: -0.1700

Data Index: 7434677 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 1.8169. Min Range: -1.8169

Max Act: 1.7049. Min Act: -0.1700

Data Index: 819945 (Open Web Text)

Max Activating Token Index: 1010