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

Dataset: Open Web Text

Neuron 1190 in Layer 3

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: 4.2650. Min Range: -4.2650

Max Act: 4.2650. Min Act: -0.1700

Data Index: 5202459 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.1151. Min Act: -0.1700

Data Index: 1108935 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0593. Min Act: -0.1700

Data Index: 7732481 (Open Web Text)

Max Activating Token Index: 95

Text #3

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0764. Min Act: -0.1700

Data Index: 1622367 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0469. Min Act: -0.1699

Data Index: 2511761 (Open Web Text)

Max Activating Token Index: 242

Text #5

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9780. Min Act: -0.1700

Data Index: 5467038 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9724. Min Act: -0.1700

Data Index: 5981434 (Open Web Text)

Max Activating Token Index: 444

Text #7

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9994. Min Act: -0.1700

Data Index: 126285 (Open Web Text)

Max Activating Token Index: 520

Text #8

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9959. Min Act: -0.1700

Data Index: 2511757 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9653. Min Act: -0.1700

Data Index: 3725180 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9286. Min Act: -0.1700

Data Index: 3304709 (Open Web Text)

Max Activating Token Index: 749

Text #11

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9516. Min Act: -0.1700

Data Index: 7732478 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9026. Min Act: -0.1700

Data Index: 7395818 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9146. Min Act: -0.1700

Data Index: 8179431 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.9091. Min Act: -0.1700

Data Index: 3626021 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.8938. Min Act: -0.1700

Data Index: 2511760 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.8791. Min Act: -0.1700

Data Index: 7919171 (Open Web Text)

Max Activating Token Index: 389

Text #17

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.8464. Min Act: -0.1700

Data Index: 4852629 (Open Web Text)

Max Activating Token Index: 957

Text #18

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.8588. Min Act: -0.1700

Data Index: 1378675 (Open Web Text)

Max Activating Token Index: 630

Text #19

Max Range: 4.2650. Min Range: -4.2650

Max Act: 3.8561. Min Act: -0.1700

Data Index: 4013283 (Open Web Text)

Max Activating Token Index: 672