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

Dataset: Open Web Text

Neuron 626 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: 3.1960. Min Range: -3.1960

Max Act: 3.1960. Min Act: -0.1700

Data Index: 8553995 (Open Web Text)

Max Activating Token Index: 874

Text #1

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1799. Min Act: -0.1700

Data Index: 2380375 (Open Web Text)

Max Activating Token Index: 877

Text #2

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1335. Min Act: -0.1700

Data Index: 7863922 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1276. Min Act: -0.1700

Data Index: 5056416 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1151. Min Act: -0.1700

Data Index: 637633 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1233. Min Act: -0.1700

Data Index: 6676305 (Open Web Text)

Max Activating Token Index: 652

Text #6

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1089. Min Act: -0.1700

Data Index: 6812446 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0984. Min Act: -0.1700

Data Index: 2230704 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1259. Min Act: -0.1700

Data Index: 897686 (Open Web Text)

Max Activating Token Index: 964

Text #9

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0592. Min Act: -0.1700

Data Index: 1654362 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0939. Min Act: -0.1700

Data Index: 7288133 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.1302. Min Act: -0.1700

Data Index: 2883818 (Open Web Text)

Max Activating Token Index: 735

Text #12

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0588. Min Act: -0.1700

Data Index: 5265569 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0600. Min Act: -0.1700

Data Index: 2089800 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0833. Min Act: -0.1700

Data Index: 4228257 (Open Web Text)

Max Activating Token Index: 699

Text #15

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0649. Min Act: -0.1700

Data Index: 1078426 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0573. Min Act: -0.1700

Data Index: 6677066 (Open Web Text)

Max Activating Token Index: 827

Text #17

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0552. Min Act: -0.1700

Data Index: 6535697 (Open Web Text)

Max Activating Token Index: 779

Text #18

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0292. Min Act: -0.1700

Data Index: 6422044 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 3.1960. Min Range: -3.1960

Max Act: 3.0586. Min Act: -0.1700

Data Index: 2473416 (Open Web Text)

Max Activating Token Index: 995