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

Dataset: Open Web Text

Neuron 856 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: 1.6135. Min Range: -1.6135

Max Act: 1.6135. Min Act: -0.1700

Data Index: 2788146 (Open Web Text)

Max Activating Token Index: 709

Text #1

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.5900. Min Act: -0.1700

Data Index: 1988733 (Open Web Text)

Max Activating Token Index: 418

Text #2

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.5579. Min Act: -0.1700

Data Index: 3174454 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.5186. Min Act: -0.1700

Data Index: 2200928 (Open Web Text)

Max Activating Token Index: 908

Text #4

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.5220. Min Act: -0.1700

Data Index: 2947277 (Open Web Text)

Max Activating Token Index: 204

Text #5

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4927. Min Act: -0.1700

Data Index: 1994409 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4938. Min Act: -0.1700

Data Index: 4505824 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4952. Min Act: -0.1700

Data Index: 3863912 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4847. Min Act: -0.1700

Data Index: 1921959 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4712. Min Act: -0.1700

Data Index: 176533 (Open Web Text)

Max Activating Token Index: 476

Text #10

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4684. Min Act: -0.1700

Data Index: 8242681 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4715. Min Act: -0.1700

Data Index: 629021 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4660. Min Act: -0.1700

Data Index: 148737 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4545. Min Act: -0.1700

Data Index: 8737062 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4632. Min Act: -0.1700

Data Index: 8691238 (Open Web Text)

Max Activating Token Index: 727

Text #15

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4685. Min Act: -0.1700

Data Index: 7532263 (Open Web Text)

Max Activating Token Index: 547

Text #16

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4601. Min Act: -0.1699

Data Index: 8688971 (Open Web Text)

Max Activating Token Index: 561

Text #17

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4629. Min Act: -0.1700

Data Index: 2084374 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4559. Min Act: -0.1700

Data Index: 6651777 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 1.6135. Min Range: -1.6135

Max Act: 1.4559. Min Act: -0.1700

Data Index: 2371160 (Open Web Text)

Max Activating Token Index: 570