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

Dataset: Open Web Text

Neuron 641 in Layer 3

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: 5.7994. Min Range: -5.7994

Max Act: 5.7837. Min Act: -0.1700

Data Index: 8641447 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.7994. Min Act: -0.1700

Data Index: 4415545 (Open Web Text)

Max Activating Token Index: 388

Text #2

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.5806. Min Act: -0.1700

Data Index: 2481531 (Open Web Text)

Max Activating Token Index: 261

Text #3

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.5167. Min Act: -0.1700

Data Index: 6317240 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.5053. Min Act: -0.1700

Data Index: 4272868 (Open Web Text)

Max Activating Token Index: 967

Text #5

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.4506. Min Act: -0.1700

Data Index: 4346855 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.4106. Min Act: -0.1700

Data Index: 2580746 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.4446. Min Act: -0.1695

Data Index: 4015225 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3586. Min Act: -0.1700

Data Index: 3339382 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3450. Min Act: -0.1700

Data Index: 4880411 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3861. Min Act: -0.1700

Data Index: 5904312 (Open Web Text)

Max Activating Token Index: 981

Text #11

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3924. Min Act: -0.1700

Data Index: 8233407 (Open Web Text)

Max Activating Token Index: 167

Text #12

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3411. Min Act: -0.1700

Data Index: 4976150 (Open Web Text)

Max Activating Token Index: 388

Text #13

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.4269. Min Act: -0.1700

Data Index: 2707700 (Open Web Text)

Max Activating Token Index: 420

Text #14

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3200. Min Act: -0.1700

Data Index: 6599997 (Open Web Text)

Max Activating Token Index: 507

Text #15

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3169. Min Act: -0.1700

Data Index: 1651969 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3408. Min Act: -0.1700

Data Index: 8070656 (Open Web Text)

Max Activating Token Index: 256

Text #17

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3308. Min Act: -0.1700

Data Index: 7522570 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3469. Min Act: -0.1700

Data Index: 1214185 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 5.7994. Min Range: -5.7994

Max Act: 5.3075. Min Act: -0.1700

Data Index: 8373198 (Open Web Text)

Max Activating Token Index: 61