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

Dataset: Open Web Text

Neuron 197 in Layer 4

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: 2.5962. Min Range: -2.5962

Max Act: 2.5962. Min Act: -0.1700

Data Index: 3432634 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5728. Min Act: -0.1700

Data Index: 3383140 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5339. Min Act: -0.1700

Data Index: 1867411 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5261. Min Act: -0.1700

Data Index: 8217339 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5102. Min Act: -0.1700

Data Index: 3053970 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5071. Min Act: -0.1700

Data Index: 7014572 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5109. Min Act: -0.1700

Data Index: 6466691 (Open Web Text)

Max Activating Token Index: 987

Text #7

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5001. Min Act: -0.1700

Data Index: 5379262 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5001. Min Act: -0.1700

Data Index: 7930669 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5001. Min Act: -0.1700

Data Index: 4393266 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5001. Min Act: -0.1700

Data Index: 1314617 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5001. Min Act: -0.1700

Data Index: 4227198 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.4922. Min Act: -0.1700

Data Index: 4031241 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.4979. Min Act: -0.1700

Data Index: 917701 (Open Web Text)

Max Activating Token Index: 693

Text #14

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5001. Min Act: -0.1700

Data Index: 3818551 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5001. Min Act: -0.1700

Data Index: 2751599 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.4564. Min Act: -0.1700

Data Index: 7137520 (Open Web Text)

Max Activating Token Index: 504

Text #17

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.4692. Min Act: -0.1700

Data Index: 4006237 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.4797. Min Act: -0.1700

Data Index: 3207257 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.4952. Min Act: -0.1700

Data Index: 7170381 (Open Web Text)

Max Activating Token Index: 466