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

Dataset: Open Web Text

Neuron 1782 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: 3.0236. Min Range: -3.0236

Max Act: 3.0236. Min Act: -0.1700

Data Index: 2980960 (Open Web Text)

Max Activating Token Index: 286

Text #1

Max Range: 3.0236. Min Range: -3.0236

Max Act: 3.0188. Min Act: -0.1700

Data Index: 6758069 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.9744. Min Act: -0.1700

Data Index: 5606656 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.9390. Min Act: -0.1700

Data Index: 7915803 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8853. Min Act: -0.1700

Data Index: 6822022 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8870. Min Act: -0.1700

Data Index: 7659243 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8726. Min Act: -0.1700

Data Index: 4434793 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8659. Min Act: -0.1700

Data Index: 6214864 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8459. Min Act: -0.1700

Data Index: 6666663 (Open Web Text)

Max Activating Token Index: 945

Text #9

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8276. Min Act: -0.1700

Data Index: 8555904 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8405. Min Act: -0.1700

Data Index: 1833147 (Open Web Text)

Max Activating Token Index: 737

Text #11

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8403. Min Act: -0.1700

Data Index: 8512298 (Open Web Text)

Max Activating Token Index: 717

Text #12

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8258. Min Act: -0.1700

Data Index: 7789634 (Open Web Text)

Max Activating Token Index: 198

Text #13

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8243. Min Act: -0.1700

Data Index: 1753071 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8222. Min Act: -0.1700

Data Index: 7191951 (Open Web Text)

Max Activating Token Index: 751

Text #15

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8327. Min Act: -0.1700

Data Index: 1880120 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8139. Min Act: -0.1700

Data Index: 7896535 (Open Web Text)

Max Activating Token Index: 937

Text #17

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8229. Min Act: -0.1700

Data Index: 1395626 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.7925. Min Act: -0.1700

Data Index: 7076338 (Open Web Text)

Max Activating Token Index: 984

Text #19

Max Range: 3.0236. Min Range: -3.0236

Max Act: 2.8113. Min Act: -0.1700

Data Index: 1580115 (Open Web Text)

Max Activating Token Index: 840