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

Dataset: Open Web Text

Neuron 1962 in Layer 4

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: 5.1195. Min Range: -5.1195

Max Act: 5.1195. Min Act: -0.1700

Data Index: 330740 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 5.1195. Min Range: -5.1195

Max Act: 5.1065. Min Act: -0.1700

Data Index: 5275267 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 5.1195. Min Range: -5.1195

Max Act: 5.0421. Min Act: -0.1700

Data Index: 4870944 (Open Web Text)

Max Activating Token Index: 756

Text #3

Max Range: 5.1195. Min Range: -5.1195

Max Act: 5.0337. Min Act: -0.1700

Data Index: 5482406 (Open Web Text)

Max Activating Token Index: 207

Text #4

Max Range: 5.1195. Min Range: -5.1195

Max Act: 5.0292. Min Act: -0.1700

Data Index: 6807393 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9997. Min Act: -0.1700

Data Index: 2517459 (Open Web Text)

Max Activating Token Index: 744

Text #6

Max Range: 5.1195. Min Range: -5.1195

Max Act: 5.0230. Min Act: -0.1700

Data Index: 4196489 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 5.1195. Min Range: -5.1195

Max Act: 5.0345. Min Act: -0.1700

Data Index: 8434791 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 5.1195. Min Range: -5.1195

Max Act: 5.0083. Min Act: -0.1700

Data Index: 7042947 (Open Web Text)

Max Activating Token Index: 1004

Text #9

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9795. Min Act: -0.1700

Data Index: 5034222 (Open Web Text)

Max Activating Token Index: 625

Text #10

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9775. Min Act: -0.1700

Data Index: 564252 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9726. Min Act: -0.1700

Data Index: 8503640 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9975. Min Act: -0.1700

Data Index: 6376138 (Open Web Text)

Max Activating Token Index: 192

Text #13

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9869. Min Act: -0.1700

Data Index: 4742273 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9661. Min Act: -0.1700

Data Index: 898023 (Open Web Text)

Max Activating Token Index: 195

Text #15

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9654. Min Act: -0.1700

Data Index: 6018727 (Open Web Text)

Max Activating Token Index: 122

Text #16

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9957. Min Act: -0.1700

Data Index: 8405548 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9402. Min Act: -0.1700

Data Index: 6965691 (Open Web Text)

Max Activating Token Index: 992

Text #18

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9347. Min Act: -0.1700

Data Index: 1444998 (Open Web Text)

Max Activating Token Index: 123

Text #19

Max Range: 5.1195. Min Range: -5.1195

Max Act: 4.9217. Min Act: -0.1700

Data Index: 7937355 (Open Web Text)

Max Activating Token Index: 388