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

Dataset: Open Web Text

Neuron 2028 in Layer 5

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: 3.2440. Min Range: -3.2440

Max Act: 3.2440. Min Act: -0.1700

Data Index: 2367430 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 3.2440. Min Range: -3.2440

Max Act: 3.0127. Min Act: -0.1700

Data Index: 2809055 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9369. Min Act: -0.1700

Data Index: 7232338 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9543. Min Act: -0.1700

Data Index: 5185488 (Open Web Text)

Max Activating Token Index: 740

Text #4

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9333. Min Act: -0.1700

Data Index: 3802510 (Open Web Text)

Max Activating Token Index: 330

Text #5

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9237. Min Act: -0.1700

Data Index: 3475380 (Open Web Text)

Max Activating Token Index: 763

Text #6

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9231. Min Act: -0.1700

Data Index: 7518513 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9426. Min Act: -0.1700

Data Index: 1868955 (Open Web Text)

Max Activating Token Index: 800

Text #8

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9075. Min Act: -0.1700

Data Index: 2649125 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9116. Min Act: -0.1700

Data Index: 3528463 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9169. Min Act: -0.1700

Data Index: 3820697 (Open Web Text)

Max Activating Token Index: 604

Text #11

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.9322. Min Act: -0.1700

Data Index: 3146314 (Open Web Text)

Max Activating Token Index: 944

Text #12

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8985. Min Act: -0.1700

Data Index: 7814710 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8991. Min Act: -0.1700

Data Index: 2226722 (Open Web Text)

Max Activating Token Index: 127

Text #14

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8980. Min Act: -0.1700

Data Index: 232813 (Open Web Text)

Max Activating Token Index: 783

Text #15

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8862. Min Act: -0.1700

Data Index: 2888941 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8811. Min Act: -0.1700

Data Index: 6291510 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8890. Min Act: -0.1700

Data Index: 457551 (Open Web Text)

Max Activating Token Index: 804

Text #18

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8643. Min Act: -0.1700

Data Index: 1015447 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 3.2440. Min Range: -3.2440

Max Act: 2.8468. Min Act: -0.1700

Data Index: 5927030 (Open Web Text)

Max Activating Token Index: 989