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

Dataset: Open Web Text

Neuron 2075 in Layer 0

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: 3.7873. Min Range: -3.7873

Max Act: 3.7873. Min Act: -0.1700

Data Index: 4119286 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.7791. Min Act: -0.1700

Data Index: 1669300 (Open Web Text)

Max Activating Token Index: 986

Text #2

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.7428. Min Act: -0.1700

Data Index: 2014349 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.7364. Min Act: -0.1700

Data Index: 5265774 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.7346. Min Act: -0.1700

Data Index: 6201071 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.7032. Min Act: -0.1700

Data Index: 7447561 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.7004. Min Act: -0.1700

Data Index: 631756 (Open Web Text)

Max Activating Token Index: 644

Text #7

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6811. Min Act: -0.1700

Data Index: 4000799 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6748. Min Act: -0.1700

Data Index: 6102617 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6485. Min Act: -0.1700

Data Index: 7305600 (Open Web Text)

Max Activating Token Index: 126

Text #10

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6327. Min Act: -0.1700

Data Index: 7898547 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6651. Min Act: -0.1700

Data Index: 7756574 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6737. Min Act: -0.1700

Data Index: 7558273 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6362. Min Act: -0.1700

Data Index: 5144244 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6450. Min Act: -0.1700

Data Index: 4261254 (Open Web Text)

Max Activating Token Index: 149

Text #15

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6492. Min Act: -0.1700

Data Index: 1947251 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6584. Min Act: -0.1700

Data Index: 3017549 (Open Web Text)

Max Activating Token Index: 105

Text #17

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6389. Min Act: -0.1700

Data Index: 6789388 (Open Web Text)

Max Activating Token Index: 823

Text #18

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6458. Min Act: -0.1700

Data Index: 6619814 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.6191. Min Act: -0.1700

Data Index: 565885 (Open Web Text)

Max Activating Token Index: 142