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

Dataset: Open Web Text

Neuron 1214 in Layer 1

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: 5.6184. Min Range: -5.6184

Max Act: 5.6184. Min Act: -0.1700

Data Index: 1321248 (Open Web Text)

Max Activating Token Index: 71

Text #1

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.5831. Min Act: -0.1700

Data Index: 1061256 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.5255. Min Act: -0.1700

Data Index: 8251709 (Open Web Text)

Max Activating Token Index: 813

Text #3

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.5058. Min Act: -0.1700

Data Index: 4828886 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4667. Min Act: -0.1700

Data Index: 7389393 (Open Web Text)

Max Activating Token Index: 765

Text #5

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4910. Min Act: -0.1700

Data Index: 6514567 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4464. Min Act: -0.1700

Data Index: 5250525 (Open Web Text)

Max Activating Token Index: 241

Text #7

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4581. Min Act: -0.1700

Data Index: 1617009 (Open Web Text)

Max Activating Token Index: 585

Text #8

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4250. Min Act: -0.1700

Data Index: 7108603 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4671. Min Act: -0.1700

Data Index: 5907652 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4557. Min Act: -0.1700

Data Index: 5793482 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4641. Min Act: -0.1700

Data Index: 8001169 (Open Web Text)

Max Activating Token Index: 155

Text #12

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3936. Min Act: -0.1700

Data Index: 3585737 (Open Web Text)

Max Activating Token Index: 305

Text #13

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4197. Min Act: -0.1700

Data Index: 1429803 (Open Web Text)

Max Activating Token Index: 885

Text #14

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4133. Min Act: -0.1700

Data Index: 3373017 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4129. Min Act: -0.1700

Data Index: 1343866 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3894. Min Act: -0.1700

Data Index: 4601721 (Open Web Text)

Max Activating Token Index: 908

Text #17

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.3744. Min Act: -0.1700

Data Index: 5688918 (Open Web Text)

Max Activating Token Index: 964

Text #18

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4319. Min Act: -0.1700

Data Index: 2606206 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 5.6184. Min Range: -5.6184

Max Act: 5.4327. Min Act: -0.1700

Data Index: 388030 (Open Web Text)

Max Activating Token Index: 256