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

Dataset: Open Web Text

Neuron 484 in Layer 5

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: 5.9727. Min Range: -5.9727

Max Act: 5.9727. Min Act: -0.1700

Data Index: 4511560 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.8945. Min Act: -0.1700

Data Index: 1122754 (Open Web Text)

Max Activating Token Index: 112

Text #2

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.8654. Min Act: -0.1700

Data Index: 3494655 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.8453. Min Act: -0.1700

Data Index: 5797827 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.8029. Min Act: -0.1700

Data Index: 8413519 (Open Web Text)

Max Activating Token Index: 139

Text #5

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.6719. Min Act: -0.1700

Data Index: 6240933 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.6443. Min Act: -0.1700

Data Index: 6091469 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.6389. Min Act: -0.1700

Data Index: 4279332 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.6750. Min Act: -0.1700

Data Index: 4552524 (Open Web Text)

Max Activating Token Index: 67

Text #9

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.6241. Min Act: -0.1700

Data Index: 5471199 (Open Web Text)

Max Activating Token Index: 370

Text #10

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.6090. Min Act: -0.1700

Data Index: 6895802 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5662. Min Act: -0.1700

Data Index: 3721625 (Open Web Text)

Max Activating Token Index: 104

Text #12

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5987. Min Act: -0.1700

Data Index: 3921234 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5777. Min Act: -0.1700

Data Index: 657356 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5898. Min Act: -0.1700

Data Index: 7366117 (Open Web Text)

Max Activating Token Index: 30

Text #15

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5767. Min Act: -0.1700

Data Index: 1080991 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5666. Min Act: -0.1700

Data Index: 4731048 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5277. Min Act: -0.1700

Data Index: 7474943 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5676. Min Act: -0.1700

Data Index: 2159925 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 5.9727. Min Range: -5.9727

Max Act: 5.5431. Min Act: -0.1700

Data Index: 5226983 (Open Web Text)

Max Activating Token Index: 903