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

Dataset: Open Web Text

Neuron 503 in Layer 0

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: 1.6105. Min Range: -1.6105

Max Act: 1.6105. Min Act: -0.1700

Data Index: 5025458 (Open Web Text)

Max Activating Token Index: 885

Text #1

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.6053. Min Act: -0.1700

Data Index: 4346919 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5883. Min Act: -0.1700

Data Index: 981868 (Open Web Text)

Max Activating Token Index: 872

Text #3

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5941. Min Act: -0.1700

Data Index: 5673722 (Open Web Text)

Max Activating Token Index: 303

Text #4

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5826. Min Act: -0.1700

Data Index: 1593905 (Open Web Text)

Max Activating Token Index: 330

Text #5

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5771. Min Act: -0.1700

Data Index: 6675974 (Open Web Text)

Max Activating Token Index: 900

Text #6

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5547. Min Act: -0.1700

Data Index: 1652274 (Open Web Text)

Max Activating Token Index: 876

Text #7

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5544. Min Act: -0.1700

Data Index: 933064 (Open Web Text)

Max Activating Token Index: 895

Text #8

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5554. Min Act: -0.1700

Data Index: 2892020 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5319. Min Act: -0.1699

Data Index: 5673721 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5376. Min Act: -0.1700

Data Index: 534180 (Open Web Text)

Max Activating Token Index: 299

Text #11

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5315. Min Act: -0.1700

Data Index: 224609 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5203. Min Act: -0.1700

Data Index: 7865674 (Open Web Text)

Max Activating Token Index: 875

Text #13

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5009. Min Act: -0.1700

Data Index: 2936548 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5173. Min Act: -0.1700

Data Index: 6626202 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.4984. Min Act: -0.1700

Data Index: 3408293 (Open Web Text)

Max Activating Token Index: 299

Text #16

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5174. Min Act: -0.1700

Data Index: 8017786 (Open Web Text)

Max Activating Token Index: 864

Text #17

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5001. Min Act: -0.1700

Data Index: 6380321 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.4941. Min Act: -0.1700

Data Index: 6087128 (Open Web Text)

Max Activating Token Index: 874

Text #19

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.4869. Min Act: -0.1700

Data Index: 6376424 (Open Web Text)

Max Activating Token Index: 869