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

Dataset: Open Web Text

Neuron 2184 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: 4.4469. Min Range: -4.4469

Max Act: 4.4469. Min Act: -0.1700

Data Index: 7649578 (Open Web Text)

Max Activating Token Index: 130

Text #1

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.4342. Min Act: -0.1700

Data Index: 483851 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.3094. Min Act: -0.1700

Data Index: 3547310 (Open Web Text)

Max Activating Token Index: 765

Text #3

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2778. Min Act: -0.1700

Data Index: 2959149 (Open Web Text)

Max Activating Token Index: 175

Text #4

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2930. Min Act: -0.1700

Data Index: 1893359 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2770. Min Act: -0.1700

Data Index: 8229347 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2967. Min Act: -0.1700

Data Index: 4107011 (Open Web Text)

Max Activating Token Index: 999

Text #7

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2648. Min Act: -0.1700

Data Index: 743299 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2407. Min Act: -0.1700

Data Index: 7778112 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2526. Min Act: -0.1700

Data Index: 6094489 (Open Web Text)

Max Activating Token Index: 637

Text #10

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2058. Min Act: -0.1700

Data Index: 7404153 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2136. Min Act: -0.1700

Data Index: 2706714 (Open Web Text)

Max Activating Token Index: 320

Text #12

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2159. Min Act: -0.1700

Data Index: 6749169 (Open Web Text)

Max Activating Token Index: 91

Text #13

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2349. Min Act: -0.1700

Data Index: 3709626 (Open Web Text)

Max Activating Token Index: 621

Text #14

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2273. Min Act: -0.1700

Data Index: 5323124 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2188. Min Act: -0.1700

Data Index: 5252198 (Open Web Text)

Max Activating Token Index: 185

Text #16

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2423. Min Act: -0.1700

Data Index: 1972486 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.2343. Min Act: -0.1700

Data Index: 705898 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.1755. Min Act: -0.1700

Data Index: 3942042 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 4.4469. Min Range: -4.4469

Max Act: 4.1690. Min Act: -0.1700

Data Index: 4094121 (Open Web Text)

Max Activating Token Index: 989