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

Dataset: Open Web Text

Neuron 597 in Layer 6

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: 8.1939. Min Range: -8.1939

Max Act: 8.1939. Min Act: -0.1700

Data Index: 855031 (Open Web Text)

Max Activating Token Index: 498

Text #1

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.6468. Min Act: -0.1700

Data Index: 2168323 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.6422. Min Act: -0.1700

Data Index: 4477818 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.5604. Min Act: -0.1700

Data Index: 6896586 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.5943. Min Act: -0.1700

Data Index: 3402707 (Open Web Text)

Max Activating Token Index: 400

Text #5

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.5522. Min Act: -0.1700

Data Index: 3082831 (Open Web Text)

Max Activating Token Index: 403

Text #6

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.4876. Min Act: -0.1700

Data Index: 3274120 (Open Web Text)

Max Activating Token Index: 147

Text #7

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.3705. Min Act: -0.1700

Data Index: 2706926 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.3811. Min Act: -0.1700

Data Index: 53111 (Open Web Text)

Max Activating Token Index: 304

Text #9

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.3429. Min Act: -0.1700

Data Index: 916734 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.3276. Min Act: -0.1700

Data Index: 1740470 (Open Web Text)

Max Activating Token Index: 757

Text #11

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.3102. Min Act: -0.1700

Data Index: 2756949 (Open Web Text)

Max Activating Token Index: 759

Text #12

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.2816. Min Act: -0.1700

Data Index: 8638554 (Open Web Text)

Max Activating Token Index: 994

Text #13

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.2699. Min Act: -0.1700

Data Index: 5301438 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.3157. Min Act: -0.1700

Data Index: 8324586 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.2687. Min Act: -0.1700

Data Index: 4747625 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.1927. Min Act: -0.1700

Data Index: 170163 (Open Web Text)

Max Activating Token Index: 379

Text #17

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.2326. Min Act: -0.1700

Data Index: 3154347 (Open Web Text)

Max Activating Token Index: 900

Text #18

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.2285. Min Act: -0.1700

Data Index: 7311319 (Open Web Text)

Max Activating Token Index: 779

Text #19

Max Range: 8.1939. Min Range: -8.1939

Max Act: 7.2327. Min Act: -0.1700

Data Index: 5217102 (Open Web Text)

Max Activating Token Index: 940