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

Dataset: Open Web Text

Neuron 514 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: 5.0244. Min Range: -5.0244

Max Act: 5.0244. Min Act: -0.1700

Data Index: 3656998 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9980. Min Act: -0.1700

Data Index: 2719977 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9587. Min Act: -0.1700

Data Index: 3478963 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9659. Min Act: -0.1700

Data Index: 1474812 (Open Web Text)

Max Activating Token Index: 811

Text #4

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9613. Min Act: -0.1700

Data Index: 2881276 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9510. Min Act: -0.1700

Data Index: 2150245 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9128. Min Act: -0.1700

Data Index: 3200720 (Open Web Text)

Max Activating Token Index: 611

Text #7

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9383. Min Act: -0.1700

Data Index: 2608190 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9256. Min Act: -0.1700

Data Index: 783907 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9214. Min Act: -0.1700

Data Index: 7891164 (Open Web Text)

Max Activating Token Index: 106

Text #10

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9114. Min Act: -0.1700

Data Index: 2349500 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9097. Min Act: -0.1700

Data Index: 1829078 (Open Web Text)

Max Activating Token Index: 188

Text #12

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.8957. Min Act: -0.1700

Data Index: 363775 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9115. Min Act: -0.1700

Data Index: 5711812 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.8868. Min Act: -0.1700

Data Index: 4823534 (Open Web Text)

Max Activating Token Index: 767

Text #15

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.8710. Min Act: -0.1700

Data Index: 4164432 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.8958. Min Act: -0.1700

Data Index: 8723211 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.9149. Min Act: -0.1700

Data Index: 1710323 (Open Web Text)

Max Activating Token Index: 852

Text #18

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.8813. Min Act: -0.1700

Data Index: 4093365 (Open Web Text)

Max Activating Token Index: 797

Text #19

Max Range: 5.0244. Min Range: -5.0244

Max Act: 4.8398. Min Act: -0.1700

Data Index: 3053681 (Open Web Text)

Max Activating Token Index: 520