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

Dataset: Open Web Text

Neuron 1952 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: 1.8058. Min Range: -1.8058

Max Act: 1.8058. Min Act: -0.1700

Data Index: 6402343 (Open Web Text)

Max Activating Token Index: 702

Text #1

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.8044. Min Act: -0.1700

Data Index: 6753552 (Open Web Text)

Max Activating Token Index: 303

Text #2

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7652. Min Act: -0.1700

Data Index: 358141 (Open Web Text)

Max Activating Token Index: 465

Text #3

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7642. Min Act: -0.1700

Data Index: 6484744 (Open Web Text)

Max Activating Token Index: 103

Text #4

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7657. Min Act: -0.1700

Data Index: 1911658 (Open Web Text)

Max Activating Token Index: 81

Text #5

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7598. Min Act: -0.1700

Data Index: 8689541 (Open Web Text)

Max Activating Token Index: 168

Text #6

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7557. Min Act: -0.1700

Data Index: 4226998 (Open Web Text)

Max Activating Token Index: 885

Text #7

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7453. Min Act: -0.1700

Data Index: 8477635 (Open Web Text)

Max Activating Token Index: 95

Text #8

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7453. Min Act: -0.1700

Data Index: 1488216 (Open Web Text)

Max Activating Token Index: 237

Text #9

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7400. Min Act: -0.1699

Data Index: 6747003 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7330. Min Act: -0.1700

Data Index: 2800718 (Open Web Text)

Max Activating Token Index: 334

Text #11

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7377. Min Act: -0.1700

Data Index: 2650016 (Open Web Text)

Max Activating Token Index: 649

Text #12

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7387. Min Act: -0.1700

Data Index: 3570921 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7345. Min Act: -0.1700

Data Index: 8495210 (Open Web Text)

Max Activating Token Index: 206

Text #14

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7309. Min Act: -0.1700

Data Index: 7029045 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7241. Min Act: -0.1700

Data Index: 4946175 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7211. Min Act: -0.1700

Data Index: 6432429 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7310. Min Act: -0.1700

Data Index: 1957654 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7266. Min Act: -0.1700

Data Index: 1601712 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.8058. Min Range: -1.8058

Max Act: 1.7252. Min Act: -0.1700

Data Index: 8034594 (Open Web Text)

Max Activating Token Index: 896