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

Dataset: Open Web Text

Neuron 2885 in Layer 1

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: 1.9105. Min Range: -1.9105

Max Act: 1.9105. Min Act: -0.1700

Data Index: 1636095 (Open Web Text)

Max Activating Token Index: 158

Text #1

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.9007. Min Act: -0.1700

Data Index: 805467 (Open Web Text)

Max Activating Token Index: 533

Text #2

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8665. Min Act: -0.1700

Data Index: 3728281 (Open Web Text)

Max Activating Token Index: 510

Text #3

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8560. Min Act: -0.1700

Data Index: 2982825 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8508. Min Act: -0.1700

Data Index: 7564165 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8337. Min Act: -0.1700

Data Index: 7144253 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8286. Min Act: -0.1700

Data Index: 3832988 (Open Web Text)

Max Activating Token Index: 934

Text #7

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8254. Min Act: -0.1700

Data Index: 3742410 (Open Web Text)

Max Activating Token Index: 693

Text #8

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8147. Min Act: -0.1700

Data Index: 5793153 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8184. Min Act: -0.1700

Data Index: 989040 (Open Web Text)

Max Activating Token Index: 555

Text #10

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8089. Min Act: -0.1700

Data Index: 6956579 (Open Web Text)

Max Activating Token Index: 230

Text #11

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8158. Min Act: -0.1700

Data Index: 6285379 (Open Web Text)

Max Activating Token Index: 277

Text #12

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8018. Min Act: -0.1700

Data Index: 4006901 (Open Web Text)

Max Activating Token Index: 513

Text #13

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7996. Min Act: -0.1700

Data Index: 4025412 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8032. Min Act: -0.1700

Data Index: 8277008 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8034. Min Act: -0.1700

Data Index: 2247168 (Open Web Text)

Max Activating Token Index: 419

Text #16

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8019. Min Act: -0.1700

Data Index: 5008933 (Open Web Text)

Max Activating Token Index: 703

Text #17

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7954. Min Act: -0.1700

Data Index: 3383000 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7977. Min Act: -0.1700

Data Index: 6896071 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7827. Min Act: -0.1700

Data Index: 1866935 (Open Web Text)

Max Activating Token Index: 416