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

Dataset: Open Web Text

Neuron 843 in Layer 6

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: 4.9223. Min Range: -4.9223

Max Act: 4.8672. Min Act: -0.1700

Data Index: 1738845 (Open Web Text)

Max Activating Token Index: 741

Text #1

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.8731. Min Act: -0.1700

Data Index: 2615338 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.9223. Min Act: -0.1700

Data Index: 4908419 (Open Web Text)

Max Activating Token Index: 341

Text #3

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.8685. Min Act: -0.1700

Data Index: 5457528 (Open Web Text)

Max Activating Token Index: 1016

Text #4

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.8312. Min Act: -0.1700

Data Index: 5142606 (Open Web Text)

Max Activating Token Index: 281

Text #5

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.8074. Min Act: -0.1700

Data Index: 7804133 (Open Web Text)

Max Activating Token Index: 1015

Text #6

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7910. Min Act: -0.1700

Data Index: 7847636 (Open Web Text)

Max Activating Token Index: 694

Text #7

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7827. Min Act: -0.1700

Data Index: 7437267 (Open Web Text)

Max Activating Token Index: 711

Text #8

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.8188. Min Act: -0.1700

Data Index: 1008158 (Open Web Text)

Max Activating Token Index: 187

Text #9

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7598. Min Act: -0.1700

Data Index: 1831680 (Open Web Text)

Max Activating Token Index: 339

Text #10

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7772. Min Act: -0.1700

Data Index: 3045606 (Open Web Text)

Max Activating Token Index: 844

Text #11

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7547. Min Act: -0.1700

Data Index: 8725445 (Open Web Text)

Max Activating Token Index: 307

Text #12

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7752. Min Act: -0.1700

Data Index: 8280906 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7123. Min Act: -0.1700

Data Index: 7601828 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7411. Min Act: -0.1700

Data Index: 4770597 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7339. Min Act: -0.1700

Data Index: 5247555 (Open Web Text)

Max Activating Token Index: 673

Text #16

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7363. Min Act: -0.1700

Data Index: 4800690 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7424. Min Act: -0.1700

Data Index: 6872796 (Open Web Text)

Max Activating Token Index: 274

Text #18

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7568. Min Act: -0.1700

Data Index: 1061951 (Open Web Text)

Max Activating Token Index: 199

Text #19

Max Range: 4.9223. Min Range: -4.9223

Max Act: 4.7365. Min Act: -0.1700

Data Index: 28486 (Open Web Text)

Max Activating Token Index: 573