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

Dataset: Open Web Text

Neuron 2603 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: 5.4651. Min Range: -5.4651

Max Act: 5.4651. Min Act: -0.1700

Data Index: 5932448 (Open Web Text)

Max Activating Token Index: 954

Text #1

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.4287. Min Act: -0.1700

Data Index: 3451713 (Open Web Text)

Max Activating Token Index: 959

Text #2

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.3754. Min Act: -0.1700

Data Index: 4472155 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.3861. Min Act: -0.1700

Data Index: 6744807 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.3285. Min Act: -0.1700

Data Index: 2679760 (Open Web Text)

Max Activating Token Index: 273

Text #5

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.3406. Min Act: -0.1700

Data Index: 4685533 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.3367. Min Act: -0.1700

Data Index: 2732138 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.3592. Min Act: -0.1700

Data Index: 5865565 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2571. Min Act: -0.1700

Data Index: 6384103 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2700. Min Act: -0.1700

Data Index: 3943401 (Open Web Text)

Max Activating Token Index: 852

Text #10

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2547. Min Act: -0.1700

Data Index: 7759008 (Open Web Text)

Max Activating Token Index: 807

Text #11

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2934. Min Act: -0.1700

Data Index: 2819265 (Open Web Text)

Max Activating Token Index: 705

Text #12

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2833. Min Act: -0.1700

Data Index: 4064162 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2290. Min Act: -0.1700

Data Index: 2888992 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2469. Min Act: -0.1700

Data Index: 3065441 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2349. Min Act: -0.1700

Data Index: 1533394 (Open Web Text)

Max Activating Token Index: 191

Text #16

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2513. Min Act: -0.1700

Data Index: 6663341 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2294. Min Act: -0.1700

Data Index: 7002055 (Open Web Text)

Max Activating Token Index: 296

Text #18

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2163. Min Act: -0.1700

Data Index: 2148206 (Open Web Text)

Max Activating Token Index: 887

Text #19

Max Range: 5.4651. Min Range: -5.4651

Max Act: 5.2035. Min Act: -0.1700

Data Index: 2689342 (Open Web Text)

Max Activating Token Index: 415