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

Dataset: Open Web Text

Neuron 1672 in Layer 1

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: 4.8207. Min Range: -4.8207

Max Act: 4.8207. Min Act: -0.1700

Data Index: 7005737 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.7722. Min Act: -0.1700

Data Index: 7005748 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.7542. Min Act: -0.1700

Data Index: 5906848 (Open Web Text)

Max Activating Token Index: 543

Text #3

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.6967. Min Act: -0.1700

Data Index: 5906857 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.6377. Min Act: -0.1700

Data Index: 4879888 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.5465. Min Act: -0.1700

Data Index: 3885831 (Open Web Text)

Max Activating Token Index: 331

Text #6

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.5255. Min Act: -0.1700

Data Index: 6366509 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.5005. Min Act: -0.1700

Data Index: 6366515 (Open Web Text)

Max Activating Token Index: 308

Text #8

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4872. Min Act: -0.1700

Data Index: 7122761 (Open Web Text)

Max Activating Token Index: 802

Text #9

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4392. Min Act: -0.1700

Data Index: 5219338 (Open Web Text)

Max Activating Token Index: 270

Text #10

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4665. Min Act: -0.1700

Data Index: 1527130 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4408. Min Act: -0.1700

Data Index: 5657920 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4585. Min Act: -0.1700

Data Index: 8766910 (Open Web Text)

Max Activating Token Index: 396

Text #13

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4670. Min Act: -0.1700

Data Index: 5326623 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4449. Min Act: -0.1700

Data Index: 7783057 (Open Web Text)

Max Activating Token Index: 956

Text #15

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4591. Min Act: -0.1700

Data Index: 1527122 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4409. Min Act: -0.1700

Data Index: 4879890 (Open Web Text)

Max Activating Token Index: 87

Text #17

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4531. Min Act: -0.1700

Data Index: 7783048 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4330. Min Act: -0.1700

Data Index: 2774645 (Open Web Text)

Max Activating Token Index: 137

Text #19

Max Range: 4.8207. Min Range: -4.8207

Max Act: 4.4258. Min Act: -0.1700

Data Index: 2588838 (Open Web Text)

Max Activating Token Index: 993