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

Dataset: Open Web Text

Neuron 558 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: 3.3870. Min Range: -3.3870

Max Act: 3.3870. Min Act: -0.1700

Data Index: 7509423 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3613. Min Act: -0.1700

Data Index: 6954574 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3142. Min Act: -0.1700

Data Index: 5041311 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3328. Min Act: -0.1700

Data Index: 4427431 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3138. Min Act: -0.1700

Data Index: 74130 (Open Web Text)

Max Activating Token Index: 168

Text #5

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3282. Min Act: -0.1700

Data Index: 5224906 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3214. Min Act: -0.1700

Data Index: 1888151 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2910. Min Act: -0.1700

Data Index: 4292360 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2926. Min Act: -0.1700

Data Index: 4455624 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2979. Min Act: -0.1700

Data Index: 2640363 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2931. Min Act: -0.1700

Data Index: 7205644 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2733. Min Act: -0.1700

Data Index: 5122935 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2721. Min Act: -0.1700

Data Index: 4158548 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2762. Min Act: -0.1700

Data Index: 8687257 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2737. Min Act: -0.1700

Data Index: 2014489 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2635. Min Act: -0.1700

Data Index: 5683456 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2678. Min Act: -0.1700

Data Index: 819165 (Open Web Text)

Max Activating Token Index: 236

Text #17

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2545. Min Act: -0.1700

Data Index: 4707174 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2549. Min Act: -0.1700

Data Index: 4323489 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2571. Min Act: -0.1700

Data Index: 5766518 (Open Web Text)

Max Activating Token Index: 14