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

Dataset: Open Web Text

Neuron 1960 in Layer 2

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: 4.6380. Min Range: -4.6380

Max Act: 4.6380. Min Act: -0.1700

Data Index: 1642053 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.5303. Min Act: -0.1700

Data Index: 7904627 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.5061. Min Act: -0.1700

Data Index: 1871349 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.5484. Min Act: -0.1700

Data Index: 6188333 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.4563. Min Act: -0.1700

Data Index: 6133525 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.4538. Min Act: -0.1700

Data Index: 3854175 (Open Web Text)

Max Activating Token Index: 427

Text #6

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.4113. Min Act: -0.1700

Data Index: 6963319 (Open Web Text)

Max Activating Token Index: 332

Text #7

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.4109. Min Act: -0.1700

Data Index: 6259894 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.3743. Min Act: -0.1700

Data Index: 7862493 (Open Web Text)

Max Activating Token Index: 918

Text #9

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.3747. Min Act: -0.1700

Data Index: 8801351 (Open Web Text)

Max Activating Token Index: 566

Text #10

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.3341. Min Act: -0.1700

Data Index: 6241260 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.3443. Min Act: -0.1700

Data Index: 1364074 (Open Web Text)

Max Activating Token Index: 407

Text #12

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.3390. Min Act: -0.1700

Data Index: 3413552 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.2933. Min Act: -0.1700

Data Index: 7727077 (Open Web Text)

Max Activating Token Index: 187

Text #14

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.2895. Min Act: -0.1700

Data Index: 443592 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.2603. Min Act: -0.1700

Data Index: 4439033 (Open Web Text)

Max Activating Token Index: 973

Text #16

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.2922. Min Act: -0.1700

Data Index: 2576507 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.2946. Min Act: -0.1700

Data Index: 5774058 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.2740. Min Act: -0.1700

Data Index: 8158760 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 4.6380. Min Range: -4.6380

Max Act: 4.2971. Min Act: -0.1700

Data Index: 5647614 (Open Web Text)

Max Activating Token Index: 904