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

Dataset: Open Web Text

Neuron 2100 in Layer 1

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: 2.4005. Min Range: -2.4005

Max Act: 2.4005. Min Act: -0.1700

Data Index: 4120069 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2806. Min Act: -0.1700

Data Index: 521563 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2358. Min Act: -0.1700

Data Index: 7393117 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2322. Min Act: -0.1700

Data Index: 5732652 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2370. Min Act: -0.1700

Data Index: 7833304 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2248. Min Act: -0.1700

Data Index: 3894851 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2282. Min Act: -0.1700

Data Index: 1297032 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2248. Min Act: -0.1700

Data Index: 5092460 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2085. Min Act: -0.1700

Data Index: 5428888 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1880. Min Act: -0.1700

Data Index: 4475964 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1917. Min Act: -0.1700

Data Index: 7367998 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1967. Min Act: -0.1700

Data Index: 2991599 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1882. Min Act: -0.1700

Data Index: 1031675 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1947. Min Act: -0.1700

Data Index: 2062002 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1987. Min Act: -0.1700

Data Index: 6444662 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1989. Min Act: -0.1700

Data Index: 5911074 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1864. Min Act: -0.1700

Data Index: 5774302 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.2012. Min Act: -0.1700

Data Index: 1754107 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1850. Min Act: -0.1700

Data Index: 3431695 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.4005. Min Range: -2.4005

Max Act: 2.1850. Min Act: -0.1700

Data Index: 5674935 (Open Web Text)

Max Activating Token Index: 4