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

Dataset: Open Web Text

Neuron 2823 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: 4.0096. Min Range: -4.0096

Max Act: 4.0096. Min Act: -0.1700

Data Index: 6154442 (Open Web Text)

Max Activating Token Index: 149

Text #1

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9940. Min Act: -0.1700

Data Index: 2502150 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9674. Min Act: -0.1700

Data Index: 1932702 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9159. Min Act: -0.1700

Data Index: 635543 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9259. Min Act: -0.1700

Data Index: 1851879 (Open Web Text)

Max Activating Token Index: 307

Text #5

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9361. Min Act: -0.1700

Data Index: 1774646 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9069. Min Act: -0.1700

Data Index: 8397723 (Open Web Text)

Max Activating Token Index: 895

Text #7

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8857. Min Act: -0.1700

Data Index: 4531239 (Open Web Text)

Max Activating Token Index: 670

Text #8

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8978. Min Act: -0.1700

Data Index: 2750154 (Open Web Text)

Max Activating Token Index: 211

Text #9

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8872. Min Act: -0.1700

Data Index: 5394932 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.9156. Min Act: -0.1700

Data Index: 7655429 (Open Web Text)

Max Activating Token Index: 268

Text #11

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8418. Min Act: -0.1700

Data Index: 7277271 (Open Web Text)

Max Activating Token Index: 798

Text #12

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8559. Min Act: -0.1700

Data Index: 1736315 (Open Web Text)

Max Activating Token Index: 602

Text #13

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8496. Min Act: -0.1700

Data Index: 4981444 (Open Web Text)

Max Activating Token Index: 666

Text #14

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8611. Min Act: -0.1700

Data Index: 7639749 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8222. Min Act: -0.1700

Data Index: 5850545 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8371. Min Act: -0.1700

Data Index: 2141060 (Open Web Text)

Max Activating Token Index: 99

Text #17

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8260. Min Act: -0.1700

Data Index: 7633941 (Open Web Text)

Max Activating Token Index: 322

Text #18

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.8120. Min Act: -0.1700

Data Index: 7088441 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 4.0096. Min Range: -4.0096

Max Act: 3.7842. Min Act: -0.1700

Data Index: 6637758 (Open Web Text)

Max Activating Token Index: 544