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

Dataset: Open Web Text

Neuron 465 in Layer 3

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: 3.2129. Min Range: -3.2129

Max Act: 3.2129. Min Act: -0.1700

Data Index: 6424603 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.1565. Min Act: -0.1700

Data Index: 5325995 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.1515. Min Act: -0.1700

Data Index: 3253207 (Open Web Text)

Max Activating Token Index: 445

Text #3

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.1296. Min Act: -0.1700

Data Index: 2880222 (Open Web Text)

Max Activating Token Index: 725

Text #4

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.1206. Min Act: -0.1700

Data Index: 5326000 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.1083. Min Act: -0.1700

Data Index: 6370575 (Open Web Text)

Max Activating Token Index: 250

Text #6

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0847. Min Act: -0.1700

Data Index: 2805815 (Open Web Text)

Max Activating Token Index: 664

Text #7

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0939. Min Act: -0.1700

Data Index: 757741 (Open Web Text)

Max Activating Token Index: 915

Text #8

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0859. Min Act: -0.1700

Data Index: 503634 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0652. Min Act: -0.1700

Data Index: 7927169 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0867. Min Act: -0.1700

Data Index: 4335166 (Open Web Text)

Max Activating Token Index: 803

Text #11

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0592. Min Act: -0.1700

Data Index: 1734180 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0487. Min Act: -0.1700

Data Index: 838470 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0674. Min Act: -0.1700

Data Index: 8067824 (Open Web Text)

Max Activating Token Index: 399

Text #14

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0630. Min Act: -0.1700

Data Index: 6424587 (Open Web Text)

Max Activating Token Index: 242

Text #15

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0158. Min Act: -0.1700

Data Index: 908307 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0182. Min Act: -0.1700

Data Index: 5047423 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0381. Min Act: -0.1700

Data Index: 1925301 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0414. Min Act: -0.1700

Data Index: 5325994 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 3.2129. Min Range: -3.2129

Max Act: 3.0413. Min Act: -0.1700

Data Index: 689902 (Open Web Text)

Max Activating Token Index: 341