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

Dataset: Open Web Text

Neuron 2060 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: 4.7038. Min Range: -4.7038

Max Act: 4.7038. Min Act: -0.1700

Data Index: 369977 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.6830. Min Act: -0.1700

Data Index: 2281040 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.6671. Min Act: -0.1700

Data Index: 6715802 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.6226. Min Act: -0.1700

Data Index: 7965181 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.6027. Min Act: -0.1700

Data Index: 456016 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.6186. Min Act: -0.1700

Data Index: 8390769 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.5955. Min Act: -0.1700

Data Index: 8105707 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.5830. Min Act: -0.1700

Data Index: 1744815 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.5547. Min Act: -0.1700

Data Index: 4938860 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.5476. Min Act: -0.1700

Data Index: 1108201 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.5577. Min Act: -0.1700

Data Index: 6188299 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.5332. Min Act: -0.1700

Data Index: 545718 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4902. Min Act: -0.1700

Data Index: 2333382 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4752. Min Act: -0.1700

Data Index: 5348536 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4726. Min Act: -0.1700

Data Index: 5669772 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4950. Min Act: -0.1700

Data Index: 2143699 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4723. Min Act: -0.1700

Data Index: 6563858 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4617. Min Act: -0.1700

Data Index: 1862188 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4416. Min Act: -0.1700

Data Index: 1357932 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.7038. Min Range: -4.7038

Max Act: 4.4463. Min Act: -0.1700

Data Index: 6347103 (Open Web Text)

Max Activating Token Index: 5