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

Dataset: Open Web Text

Neuron 1113 in Layer 6

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: 4.9340. Min Range: -4.9340

Max Act: 4.9340. Min Act: -0.1700

Data Index: 8503665 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.9290. Min Act: -0.1700

Data Index: 8388207 (Open Web Text)

Max Activating Token Index: 863

Text #2

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.8883. Min Act: -0.1700

Data Index: 6908146 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.8861. Min Act: -0.1700

Data Index: 8169118 (Open Web Text)

Max Activating Token Index: 144

Text #4

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.8524. Min Act: -0.1700

Data Index: 8091124 (Open Web Text)

Max Activating Token Index: 970

Text #5

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.8299. Min Act: -0.1700

Data Index: 147221 (Open Web Text)

Max Activating Token Index: 581

Text #6

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7956. Min Act: -0.1700

Data Index: 4997356 (Open Web Text)

Max Activating Token Index: 954

Text #7

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7961. Min Act: -0.1700

Data Index: 5153727 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7960. Min Act: -0.1700

Data Index: 5754075 (Open Web Text)

Max Activating Token Index: 63

Text #9

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7141. Min Act: -0.1700

Data Index: 493686 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7543. Min Act: -0.1700

Data Index: 1264169 (Open Web Text)

Max Activating Token Index: 718

Text #11

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7421. Min Act: -0.1700

Data Index: 5059245 (Open Web Text)

Max Activating Token Index: 877

Text #12

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7176. Min Act: -0.1700

Data Index: 2456498 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7409. Min Act: -0.1700

Data Index: 3651154 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.6998. Min Act: -0.1700

Data Index: 300720 (Open Web Text)

Max Activating Token Index: 356

Text #15

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.6867. Min Act: -0.1700

Data Index: 5660634 (Open Web Text)

Max Activating Token Index: 858

Text #16

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.6871. Min Act: -0.1700

Data Index: 3186242 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.7058. Min Act: -0.1700

Data Index: 7001827 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.6770. Min Act: -0.1700

Data Index: 6356126 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 4.9340. Min Range: -4.9340

Max Act: 4.6694. Min Act: -0.1700

Data Index: 2026366 (Open Web Text)

Max Activating Token Index: 589