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

Dataset: Open Web Text

Neuron 708 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: 4.3721. Min Range: -4.3721

Max Act: 4.3721. Min Act: -0.1700

Data Index: 1270875 (Open Web Text)

Max Activating Token Index: 164

Text #1

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.2606. Min Act: -0.1700

Data Index: 299270 (Open Web Text)

Max Activating Token Index: 918

Text #2

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.2521. Min Act: -0.1700

Data Index: 555773 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.2077. Min Act: -0.1700

Data Index: 4870964 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.1466. Min Act: -0.1700

Data Index: 6076498 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.1339. Min Act: -0.1700

Data Index: 3254095 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.1395. Min Act: -0.1700

Data Index: 5014049 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0950. Min Act: -0.1700

Data Index: 5508699 (Open Web Text)

Max Activating Token Index: 938

Text #8

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0839. Min Act: -0.1700

Data Index: 594111 (Open Web Text)

Max Activating Token Index: 266

Text #9

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.1141. Min Act: -0.1700

Data Index: 3085216 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0730. Min Act: -0.1700

Data Index: 6368585 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0946. Min Act: -0.1700

Data Index: 1784371 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0752. Min Act: -0.1700

Data Index: 1774824 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0854. Min Act: -0.1700

Data Index: 7087246 (Open Web Text)

Max Activating Token Index: 109

Text #14

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0663. Min Act: -0.1700

Data Index: 5867141 (Open Web Text)

Max Activating Token Index: 722

Text #15

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0768. Min Act: -0.1700

Data Index: 3051482 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0902. Min Act: -0.1700

Data Index: 947753 (Open Web Text)

Max Activating Token Index: 966

Text #17

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0596. Min Act: -0.1700

Data Index: 4583942 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0621. Min Act: -0.1700

Data Index: 1479928 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 4.3721. Min Range: -4.3721

Max Act: 4.0433. Min Act: -0.1700

Data Index: 374139 (Open Web Text)

Max Activating Token Index: 25