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

Dataset: Open Web Text

Neuron 276 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: 3.9693. Min Range: -3.9693

Max Act: 3.9693. Min Act: -0.1700

Data Index: 7930777 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9643. Min Act: -0.1700

Data Index: 2046971 (Open Web Text)

Max Activating Token Index: 333

Text #2

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9466. Min Act: -0.1700

Data Index: 7416778 (Open Web Text)

Max Activating Token Index: 516

Text #3

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9462. Min Act: -0.1700

Data Index: 3677181 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9123. Min Act: -0.1700

Data Index: 6226350 (Open Web Text)

Max Activating Token Index: 376

Text #5

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8660. Min Act: -0.1700

Data Index: 4296201 (Open Web Text)

Max Activating Token Index: 301

Text #6

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8612. Min Act: -0.1700

Data Index: 8696579 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1332862 (Open Web Text)

Max Activating Token Index: 225

Text #8

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8205. Min Act: -0.1700

Data Index: 2252026 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7856. Min Act: -0.1700

Data Index: 5545204 (Open Web Text)

Max Activating Token Index: 407

Text #10

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7958. Min Act: -0.1700

Data Index: 3218398 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7967. Min Act: -0.1700

Data Index: 4761275 (Open Web Text)

Max Activating Token Index: 125

Text #12

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7862. Min Act: -0.1700

Data Index: 292718 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7640. Min Act: -0.1700

Data Index: 5754452 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7742. Min Act: -0.1700

Data Index: 841328 (Open Web Text)

Max Activating Token Index: 229

Text #15

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7770. Min Act: -0.1700

Data Index: 6418253 (Open Web Text)

Max Activating Token Index: 838

Text #16

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8093. Min Act: -0.1700

Data Index: 8013358 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7715. Min Act: -0.1700

Data Index: 8199742 (Open Web Text)

Max Activating Token Index: 609

Text #18

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7345. Min Act: -0.1700

Data Index: 1400186 (Open Web Text)

Max Activating Token Index: 784

Text #19

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.7438. Min Act: -0.1700

Data Index: 4163176 (Open Web Text)

Max Activating Token Index: 854