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

Dataset: Open Web Text

Neuron 717 in Layer 3

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: 4.5861. Min Range: -4.5861

Max Act: 4.5861. Min Act: -0.1700

Data Index: 7638468 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.5066. Min Act: -0.1700

Data Index: 42614 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.4847. Min Act: -0.1700

Data Index: 333960 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.4629. Min Act: -0.1700

Data Index: 1345084 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.4391. Min Act: -0.1700

Data Index: 1116718 (Open Web Text)

Max Activating Token Index: 641

Text #5

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.4420. Min Act: -0.1700

Data Index: 2028620 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.4250. Min Act: -0.1700

Data Index: 719367 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3884. Min Act: -0.1700

Data Index: 1101131 (Open Web Text)

Max Activating Token Index: 95

Text #8

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.4089. Min Act: -0.1700

Data Index: 3196435 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3723. Min Act: -0.1700

Data Index: 2700899 (Open Web Text)

Max Activating Token Index: 247

Text #10

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3907. Min Act: -0.1700

Data Index: 6896484 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3731. Min Act: -0.1700

Data Index: 6896483 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3860. Min Act: -0.1700

Data Index: 4839006 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3578. Min Act: -0.1700

Data Index: 4811311 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3206. Min Act: -0.1700

Data Index: 6660407 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3446. Min Act: -0.1700

Data Index: 8042411 (Open Web Text)

Max Activating Token Index: 942

Text #16

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3280. Min Act: -0.1700

Data Index: 7085750 (Open Web Text)

Max Activating Token Index: 590

Text #17

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3390. Min Act: -0.1700

Data Index: 7572512 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.3356. Min Act: -0.1700

Data Index: 3575207 (Open Web Text)

Max Activating Token Index: 227

Text #19

Max Range: 4.5861. Min Range: -4.5861

Max Act: 4.2979. Min Act: -0.1700

Data Index: 7327994 (Open Web Text)

Max Activating Token Index: 33