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

Dataset: Open Web Text

Neuron 686 in Layer 6

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: 4.3660. Min Range: -4.3660

Max Act: 4.3660. Min Act: -0.1700

Data Index: 6777478 (Open Web Text)

Max Activating Token Index: 588

Text #1

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.0422. Min Act: -0.1700

Data Index: 1341388 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.0001. Min Act: -0.1700

Data Index: 1071387 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 4.3660. Min Range: -4.3660

Max Act: 4.0275. Min Act: -0.1700

Data Index: 6046558 (Open Web Text)

Max Activating Token Index: 705

Text #4

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.9467. Min Act: -0.1700

Data Index: 5054208 (Open Web Text)

Max Activating Token Index: 917

Text #5

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.9271. Min Act: -0.1700

Data Index: 3770836 (Open Web Text)

Max Activating Token Index: 925

Text #6

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.8568. Min Act: -0.1700

Data Index: 4794886 (Open Web Text)

Max Activating Token Index: 670

Text #7

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.8332. Min Act: -0.1700

Data Index: 3309278 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.8746. Min Act: -0.1700

Data Index: 6115361 (Open Web Text)

Max Activating Token Index: 692

Text #9

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.7467. Min Act: -0.1700

Data Index: 6209989 (Open Web Text)

Max Activating Token Index: 624

Text #10

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.7470. Min Act: -0.1700

Data Index: 1420952 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.7101. Min Act: -0.1700

Data Index: 2260142 (Open Web Text)

Max Activating Token Index: 857

Text #12

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.7426. Min Act: -0.1700

Data Index: 8250408 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.6946. Min Act: -0.1700

Data Index: 6857213 (Open Web Text)

Max Activating Token Index: 239

Text #14

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.6627. Min Act: -0.1700

Data Index: 8626354 (Open Web Text)

Max Activating Token Index: 751

Text #15

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.6960. Min Act: -0.1700

Data Index: 2994262 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.6716. Min Act: -0.1700

Data Index: 4202839 (Open Web Text)

Max Activating Token Index: 99

Text #17

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.7225. Min Act: -0.1700

Data Index: 3859848 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.6845. Min Act: -0.1700

Data Index: 7034673 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 4.3660. Min Range: -4.3660

Max Act: 3.6927. Min Act: -0.1700

Data Index: 5519758 (Open Web Text)

Max Activating Token Index: 820