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

Dataset: Open Web Text

Neuron 284 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: 5.3660. Min Range: -5.3660

Max Act: 5.3660. Min Act: -0.1700

Data Index: 2440046 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.3586. Min Act: -0.1700

Data Index: 6103026 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.3141. Min Act: -0.1700

Data Index: 2430147 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.3079. Min Act: -0.1700

Data Index: 1379332 (Open Web Text)

Max Activating Token Index: 277

Text #4

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.3402. Min Act: -0.1700

Data Index: 5459042 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2787. Min Act: -0.1700

Data Index: 1674837 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2426. Min Act: -0.1700

Data Index: 8719026 (Open Web Text)

Max Activating Token Index: 203

Text #7

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2428. Min Act: -0.1700

Data Index: 3310011 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2561. Min Act: -0.1700

Data Index: 5404452 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2558. Min Act: -0.1700

Data Index: 367975 (Open Web Text)

Max Activating Token Index: 840

Text #10

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2561. Min Act: -0.1700

Data Index: 4311538 (Open Web Text)

Max Activating Token Index: 287

Text #11

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2459. Min Act: -0.1700

Data Index: 5228168 (Open Web Text)

Max Activating Token Index: 289

Text #12

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.1596. Min Act: -0.1700

Data Index: 5284180 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2092. Min Act: -0.1700

Data Index: 4213345 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.2063. Min Act: -0.1700

Data Index: 4323528 (Open Web Text)

Max Activating Token Index: 399

Text #15

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.1583. Min Act: -0.1700

Data Index: 8483270 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.1165. Min Act: -0.1700

Data Index: 3053691 (Open Web Text)

Max Activating Token Index: 925

Text #17

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.1648. Min Act: -0.1700

Data Index: 2205488 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.1257. Min Act: -0.1700

Data Index: 5800105 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 5.3660. Min Range: -5.3660

Max Act: 5.1165. Min Act: -0.1700

Data Index: 5275838 (Open Web Text)

Max Activating Token Index: 891