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

Dataset: Open Web Text

Neuron 215 in Layer 3

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: 3.4963. Min Range: -3.4963

Max Act: 3.4963. Min Act: -0.1700

Data Index: 3914546 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.3546. Min Act: -0.1700

Data Index: 2263607 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.3370. Min Act: -0.1700

Data Index: 2826112 (Open Web Text)

Max Activating Token Index: 490

Text #3

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.3273. Min Act: -0.1700

Data Index: 8513801 (Open Web Text)

Max Activating Token Index: 868

Text #4

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.3635. Min Act: -0.1700

Data Index: 4981202 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.3055. Min Act: -0.1700

Data Index: 3013336 (Open Web Text)

Max Activating Token Index: 387

Text #6

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.3069. Min Act: -0.1700

Data Index: 2615319 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2765. Min Act: -0.1700

Data Index: 3586191 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2394. Min Act: -0.1700

Data Index: 1594999 (Open Web Text)

Max Activating Token Index: 674

Text #9

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2467. Min Act: -0.1700

Data Index: 6786898 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2372. Min Act: -0.1700

Data Index: 8215880 (Open Web Text)

Max Activating Token Index: 984

Text #11

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2818. Min Act: -0.1700

Data Index: 8375607 (Open Web Text)

Max Activating Token Index: 747

Text #12

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2525. Min Act: -0.1700

Data Index: 5093806 (Open Web Text)

Max Activating Token Index: 336

Text #13

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2313. Min Act: -0.1700

Data Index: 7374621 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2280. Min Act: -0.1700

Data Index: 834741 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2443. Min Act: -0.1700

Data Index: 1896200 (Open Web Text)

Max Activating Token Index: 412

Text #16

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2259. Min Act: -0.1700

Data Index: 5907638 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2361. Min Act: -0.1700

Data Index: 2635794 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2179. Min Act: -0.1700

Data Index: 6756136 (Open Web Text)

Max Activating Token Index: 278

Text #19

Max Range: 3.4963. Min Range: -3.4963

Max Act: 3.2224. Min Act: -0.1700

Data Index: 5346827 (Open Web Text)

Max Activating Token Index: 258