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

Dataset: Open Web Text

Neuron 1111 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: 3.4177. Min Range: -3.4177

Max Act: 3.4177. Min Act: -0.1700

Data Index: 7449689 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.3418. Min Act: -0.1700

Data Index: 4765640 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2888. Min Act: -0.1700

Data Index: 4620773 (Open Web Text)

Max Activating Token Index: 876

Text #3

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2823. Min Act: -0.1700

Data Index: 4614400 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2744. Min Act: -0.1700

Data Index: 4612402 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2748. Min Act: -0.1700

Data Index: 5909036 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2307. Min Act: -0.1700

Data Index: 6563453 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2407. Min Act: -0.1700

Data Index: 8414906 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2426. Min Act: -0.1700

Data Index: 8528825 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2327. Min Act: -0.1700

Data Index: 3409951 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2376. Min Act: -0.1700

Data Index: 2381753 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2273. Min Act: -0.1700

Data Index: 3724874 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2301. Min Act: -0.1700

Data Index: 3891563 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2440. Min Act: -0.1700

Data Index: 6538194 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2122. Min Act: -0.1700

Data Index: 2978076 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2247. Min Act: -0.1700

Data Index: 4344656 (Open Web Text)

Max Activating Token Index: 719

Text #16

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2094. Min Act: -0.1700

Data Index: 4411182 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2211. Min Act: -0.1700

Data Index: 226693 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2094. Min Act: -0.1700

Data Index: 3574819 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.4177. Min Range: -3.4177

Max Act: 3.2094. Min Act: -0.1700

Data Index: 3014329 (Open Web Text)

Max Activating Token Index: 2