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

Dataset: Open Web Text

Neuron 514 in Layer 0

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: 1.6570. Min Range: -1.6570

Max Act: 1.6570. Min Act: -0.1700

Data Index: 4032445 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6312. Min Act: -0.1700

Data Index: 737862 (Open Web Text)

Max Activating Token Index: 367

Text #2

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6348. Min Act: -0.1700

Data Index: 430687 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6256. Min Act: -0.1700

Data Index: 4150235 (Open Web Text)

Max Activating Token Index: 614

Text #4

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6122. Min Act: -0.1700

Data Index: 6710850 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6204. Min Act: -0.1700

Data Index: 719821 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6201. Min Act: -0.1700

Data Index: 2683301 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6232. Min Act: -0.1700

Data Index: 2376350 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6111. Min Act: -0.1700

Data Index: 4418051 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6099. Min Act: -0.1700

Data Index: 1876367 (Open Web Text)

Max Activating Token Index: 402

Text #10

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6104. Min Act: -0.1700

Data Index: 3057871 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6205. Min Act: -0.1700

Data Index: 7328652 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6120. Min Act: -0.1700

Data Index: 6883866 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6177. Min Act: -0.1700

Data Index: 737861 (Open Web Text)

Max Activating Token Index: 352

Text #14

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.6180. Min Act: -0.1700

Data Index: 5914128 (Open Web Text)

Max Activating Token Index: 487

Text #15

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.5983. Min Act: -0.1700

Data Index: 3549848 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.5968. Min Act: -0.1700

Data Index: 2905746 (Open Web Text)

Max Activating Token Index: 61

Text #17

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.5939. Min Act: -0.1700

Data Index: 7657291 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.5992. Min Act: -0.1700

Data Index: 6723856 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 1.6570. Min Range: -1.6570

Max Act: 1.5794. Min Act: -0.1700

Data Index: 1146224 (Open Web Text)

Max Activating Token Index: 621