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

Dataset: Open Web Text

Neuron 531 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: 3.7645. Min Range: -3.7645

Max Act: 3.7645. Min Act: -0.1700

Data Index: 3824431 (Open Web Text)

Max Activating Token Index: 609

Text #1

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.7029. Min Act: -0.1700

Data Index: 1133257 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.7045. Min Act: -0.1700

Data Index: 1463527 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6770. Min Act: -0.1700

Data Index: 8431857 (Open Web Text)

Max Activating Token Index: 917

Text #4

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6854. Min Act: -0.1700

Data Index: 1683373 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1826599 (Open Web Text)

Max Activating Token Index: 616

Text #6

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6555. Min Act: -0.1700

Data Index: 6159140 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6411. Min Act: -0.1700

Data Index: 1293487 (Open Web Text)

Max Activating Token Index: 276

Text #8

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6581. Min Act: -0.1700

Data Index: 4110508 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6399. Min Act: -0.1700

Data Index: 3121436 (Open Web Text)

Max Activating Token Index: 334

Text #10

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6216. Min Act: -0.1700

Data Index: 2180075 (Open Web Text)

Max Activating Token Index: 872

Text #11

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6022. Min Act: -0.1700

Data Index: 3869506 (Open Web Text)

Max Activating Token Index: 337

Text #12

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6344. Min Act: -0.1700

Data Index: 4338421 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.6206. Min Act: -0.1700

Data Index: 159270 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.5903. Min Act: -0.1700

Data Index: 8400319 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.5866. Min Act: -0.1700

Data Index: 6374346 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.5739. Min Act: -0.1700

Data Index: 6306876 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.5897. Min Act: -0.1700

Data Index: 5845098 (Open Web Text)

Max Activating Token Index: 580

Text #18

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.5934. Min Act: -0.1700

Data Index: 8346500 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 3.7645. Min Range: -3.7645

Max Act: 3.5930. Min Act: -0.1700

Data Index: 122331 (Open Web Text)

Max Activating Token Index: 90