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

Dataset: Open Web Text

Neuron 1879 in Layer 4

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: 3.2079. Min Range: -3.2079

Max Act: 3.2079. Min Act: -0.1700

Data Index: 7707813 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1655. Min Act: -0.1700

Data Index: 7278422 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1291. Min Act: -0.1700

Data Index: 435355 (Open Web Text)

Max Activating Token Index: 623

Text #3

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1270. Min Act: -0.1700

Data Index: 6560469 (Open Web Text)

Max Activating Token Index: 62

Text #4

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1335. Min Act: -0.1700

Data Index: 2285638 (Open Web Text)

Max Activating Token Index: 592

Text #5

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1477. Min Act: -0.1700

Data Index: 7832824 (Open Web Text)

Max Activating Token Index: 181

Text #6

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1405. Min Act: -0.1700

Data Index: 8012889 (Open Web Text)

Max Activating Token Index: 500

Text #7

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1239. Min Act: -0.1700

Data Index: 1617184 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1323. Min Act: -0.1700

Data Index: 2080886 (Open Web Text)

Max Activating Token Index: 916

Text #9

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1300. Min Act: -0.1700

Data Index: 7349574 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1242. Min Act: -0.1700

Data Index: 7975798 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.0924. Min Act: -0.1700

Data Index: 1922082 (Open Web Text)

Max Activating Token Index: 917

Text #12

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.0960. Min Act: -0.1700

Data Index: 1121625 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1008. Min Act: -0.1700

Data Index: 5817566 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.0868. Min Act: -0.1700

Data Index: 6545606 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.1092. Min Act: -0.1700

Data Index: 6459212 (Open Web Text)

Max Activating Token Index: 947

Text #16

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.0785. Min Act: -0.1700

Data Index: 8173797 (Open Web Text)

Max Activating Token Index: 633

Text #17

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.0972. Min Act: -0.1700

Data Index: 6296263 (Open Web Text)

Max Activating Token Index: 209

Text #18

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.0985. Min Act: -0.1700

Data Index: 6280763 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.0843. Min Act: -0.1700

Data Index: 6229140 (Open Web Text)

Max Activating Token Index: 445