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

Dataset: Open Web Text

Neuron 700 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: 4.9508. Min Range: -4.9508

Max Act: 4.9508. Min Act: -0.1700

Data Index: 537684 (Open Web Text)

Max Activating Token Index: 296

Text #1

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.7936. Min Act: -0.1700

Data Index: 2114101 (Open Web Text)

Max Activating Token Index: 542

Text #2

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.7133. Min Act: -0.1700

Data Index: 2778969 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.6880. Min Act: -0.1700

Data Index: 93202 (Open Web Text)

Max Activating Token Index: 925

Text #4

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.6012. Min Act: -0.1700

Data Index: 1018036 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.5202. Min Act: -0.1700

Data Index: 2606630 (Open Web Text)

Max Activating Token Index: 802

Text #6

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.5330. Min Act: -0.1700

Data Index: 8242352 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.5423. Min Act: -0.1700

Data Index: 7747326 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.5435. Min Act: -0.1700

Data Index: 3724645 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4631. Min Act: -0.1700

Data Index: 1918124 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4705. Min Act: -0.1700

Data Index: 2737200 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4750. Min Act: -0.1700

Data Index: 7914494 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4740. Min Act: -0.1700

Data Index: 2591239 (Open Web Text)

Max Activating Token Index: 805

Text #13

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.5327. Min Act: -0.1700

Data Index: 4308382 (Open Web Text)

Max Activating Token Index: 788

Text #14

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4942. Min Act: -0.1700

Data Index: 3236503 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4646. Min Act: -0.1700

Data Index: 3158828 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4188. Min Act: -0.1700

Data Index: 7068592 (Open Web Text)

Max Activating Token Index: 921

Text #17

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4576. Min Act: -0.1700

Data Index: 5996240 (Open Web Text)

Max Activating Token Index: 491

Text #18

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.4541. Min Act: -0.1700

Data Index: 4586361 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 4.9508. Min Range: -4.9508

Max Act: 4.3997. Min Act: -0.1700

Data Index: 3982534 (Open Web Text)

Max Activating Token Index: 11