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

Dataset: Open Web Text

Neuron 1512 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: 1.6203. Min Range: -1.6203

Max Act: 1.6186. Min Act: -0.1700

Data Index: 7396670 (Open Web Text)

Max Activating Token Index: 271

Text #1

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.6131. Min Act: -0.1700

Data Index: 4619393 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.6203. Min Act: -0.1700

Data Index: 6072168 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.6035. Min Act: -0.1700

Data Index: 7120730 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5970. Min Act: -0.1700

Data Index: 3552167 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5929. Min Act: -0.1700

Data Index: 425532 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5827. Min Act: -0.1700

Data Index: 3237950 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5725. Min Act: -0.1700

Data Index: 2401759 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5681. Min Act: -0.1700

Data Index: 3624056 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5516. Min Act: -0.1700

Data Index: 8825078 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5387. Min Act: -0.1698

Data Index: 2673761 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5367. Min Act: -0.1700

Data Index: 2409237 (Open Web Text)

Max Activating Token Index: 335

Text #12

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5140. Min Act: -0.1700

Data Index: 524165 (Open Web Text)

Max Activating Token Index: 877

Text #13

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5183. Min Act: -0.1700

Data Index: 3676450 (Open Web Text)

Max Activating Token Index: 307

Text #14

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5107. Min Act: -0.1700

Data Index: 107111 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5230. Min Act: -0.1700

Data Index: 5246408 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5192. Min Act: -0.1700

Data Index: 524172 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5168. Min Act: -0.1700

Data Index: 2017399 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5057. Min Act: -0.1700

Data Index: 2429532 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 1.6203. Min Range: -1.6203

Max Act: 1.5109. Min Act: -0.1700

Data Index: 4497870 (Open Web Text)

Max Activating Token Index: 675