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

Dataset: Open Web Text

Neuron 1606 in Layer 2

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: 3.6228. Min Range: -3.6228

Max Act: 3.6228. Min Act: -0.1700

Data Index: 3086402 (Open Web Text)

Max Activating Token Index: 133

Text #1

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.3478. Min Act: -0.1700

Data Index: 6662796 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.3030. Min Act: -0.1700

Data Index: 6102636 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2908. Min Act: -0.1700

Data Index: 2321703 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.3064. Min Act: -0.1700

Data Index: 7516185 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.3019. Min Act: -0.1700

Data Index: 2017247 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2801. Min Act: -0.1700

Data Index: 8069222 (Open Web Text)

Max Activating Token Index: 546

Text #7

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2902. Min Act: -0.1700

Data Index: 8174447 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2937. Min Act: -0.1700

Data Index: 8174445 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2879. Min Act: -0.1700

Data Index: 179343 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2703. Min Act: -0.1700

Data Index: 5001947 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2519. Min Act: -0.1700

Data Index: 3177627 (Open Web Text)

Max Activating Token Index: 593

Text #12

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2678. Min Act: -0.1700

Data Index: 3292696 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2587. Min Act: -0.1700

Data Index: 7049031 (Open Web Text)

Max Activating Token Index: 83

Text #14

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2552. Min Act: -0.1700

Data Index: 6039208 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2180. Min Act: -0.1700

Data Index: 5007631 (Open Web Text)

Max Activating Token Index: 937

Text #16

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2352. Min Act: -0.1700

Data Index: 5738790 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2511. Min Act: -0.1700

Data Index: 2305638 (Open Web Text)

Max Activating Token Index: 781

Text #18

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2427. Min Act: -0.1700

Data Index: 5792912 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 3.6228. Min Range: -3.6228

Max Act: 3.2510. Min Act: -0.1700

Data Index: 2558448 (Open Web Text)

Max Activating Token Index: 180