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

Dataset: Open Web Text

Neuron 586 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: 5.3575. Min Range: -5.3575

Max Act: 5.3575. Min Act: -0.1700

Data Index: 1264957 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.3496. Min Act: -0.1700

Data Index: 5921375 (Open Web Text)

Max Activating Token Index: 351

Text #2

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.3317. Min Act: -0.1700

Data Index: 2186283 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.3266. Min Act: -0.1700

Data Index: 334169 (Open Web Text)

Max Activating Token Index: 134

Text #4

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.3139. Min Act: -0.1700

Data Index: 4589483 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.3122. Min Act: -0.1700

Data Index: 46002 (Open Web Text)

Max Activating Token Index: 87

Text #6

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.3053. Min Act: -0.1700

Data Index: 8544612 (Open Web Text)

Max Activating Token Index: 815

Text #7

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2961. Min Act: -0.1700

Data Index: 4467470 (Open Web Text)

Max Activating Token Index: 562

Text #8

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2818. Min Act: -0.1700

Data Index: 1086988 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2708. Min Act: -0.1700

Data Index: 3775552 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2556. Min Act: -0.1700

Data Index: 7377995 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2469. Min Act: -0.1700

Data Index: 2083689 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2760. Min Act: -0.1700

Data Index: 2799414 (Open Web Text)

Max Activating Token Index: 726

Text #13

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2683. Min Act: -0.1700

Data Index: 7303862 (Open Web Text)

Max Activating Token Index: 963

Text #14

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2602. Min Act: -0.1700

Data Index: 4093881 (Open Web Text)

Max Activating Token Index: 266

Text #15

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2677. Min Act: -0.1700

Data Index: 7160530 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2488. Min Act: -0.1700

Data Index: 3393756 (Open Web Text)

Max Activating Token Index: 102

Text #17

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2265. Min Act: -0.1700

Data Index: 5275187 (Open Web Text)

Max Activating Token Index: 132

Text #18

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2299. Min Act: -0.1700

Data Index: 5295542 (Open Web Text)

Max Activating Token Index: 701

Text #19

Max Range: 5.3575. Min Range: -5.3575

Max Act: 5.2293. Min Act: -0.1700

Data Index: 104548 (Open Web Text)

Max Activating Token Index: 112