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

Dataset: Open Web Text

Neuron 2985 in Layer 5

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: 3.1944. Min Range: -3.1944

Max Act: 3.1944. Min Act: -0.1700

Data Index: 4559215 (Open Web Text)

Max Activating Token Index: 228

Text #1

Max Range: 3.1944. Min Range: -3.1944

Max Act: 3.0736. Min Act: -0.1700

Data Index: 4559214 (Open Web Text)

Max Activating Token Index: 751

Text #2

Max Range: 3.1944. Min Range: -3.1944

Max Act: 3.0501. Min Act: -0.1700

Data Index: 2947100 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 3.1944. Min Range: -3.1944

Max Act: 3.0003. Min Act: -0.1700

Data Index: 5613364 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 3.1944. Min Range: -3.1944

Max Act: 3.0011. Min Act: -0.1700

Data Index: 3653982 (Open Web Text)

Max Activating Token Index: 697

Text #5

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9767. Min Act: -0.1700

Data Index: 5655560 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 3.1944. Min Range: -3.1944

Max Act: 3.0137. Min Act: -0.1700

Data Index: 423575 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 3.1944. Min Range: -3.1944

Max Act: 3.0185. Min Act: -0.1700

Data Index: 8627901 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9892. Min Act: -0.1700

Data Index: 6052011 (Open Web Text)

Max Activating Token Index: 764

Text #9

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9975. Min Act: -0.1700

Data Index: 7832385 (Open Web Text)

Max Activating Token Index: 976

Text #10

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9693. Min Act: -0.1700

Data Index: 6570430 (Open Web Text)

Max Activating Token Index: 518

Text #11

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9743. Min Act: -0.1700

Data Index: 572547 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9687. Min Act: -0.1700

Data Index: 5856781 (Open Web Text)

Max Activating Token Index: 303

Text #13

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9891. Min Act: -0.1700

Data Index: 2981867 (Open Web Text)

Max Activating Token Index: 809

Text #14

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9512. Min Act: -0.1700

Data Index: 2875616 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9396. Min Act: -0.1700

Data Index: 1046239 (Open Web Text)

Max Activating Token Index: 630

Text #16

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9761. Min Act: -0.1700

Data Index: 1156383 (Open Web Text)

Max Activating Token Index: 316

Text #17

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9598. Min Act: -0.1700

Data Index: 6181219 (Open Web Text)

Max Activating Token Index: 406

Text #18

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9611. Min Act: -0.1700

Data Index: 3185358 (Open Web Text)

Max Activating Token Index: 142

Text #19

Max Range: 3.1944. Min Range: -3.1944

Max Act: 2.9591. Min Act: -0.1700

Data Index: 4553836 (Open Web Text)

Max Activating Token Index: 458