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

Dataset: Open Web Text

Neuron 656 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: 3.3951. Min Range: -3.3951

Max Act: 3.3951. Min Act: -0.1700

Data Index: 2903386 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.3027. Min Act: -0.1700

Data Index: 4101857 (Open Web Text)

Max Activating Token Index: 794

Text #2

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.1305. Min Act: -0.1700

Data Index: 6606111 (Open Web Text)

Max Activating Token Index: 324

Text #3

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.1485. Min Act: -0.1700

Data Index: 2627810 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.1248. Min Act: -0.1700

Data Index: 4412992 (Open Web Text)

Max Activating Token Index: 82

Text #5

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0947. Min Act: -0.1700

Data Index: 17661 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0782. Min Act: -0.1700

Data Index: 8436322 (Open Web Text)

Max Activating Token Index: 931

Text #7

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0795. Min Act: -0.1700

Data Index: 5743269 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.9903. Min Act: -0.1700

Data Index: 6831967 (Open Web Text)

Max Activating Token Index: 441

Text #9

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0742. Min Act: -0.1700

Data Index: 6529874 (Open Web Text)

Max Activating Token Index: 202

Text #10

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0440. Min Act: -0.1700

Data Index: 449220 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0464. Min Act: -0.1700

Data Index: 4701561 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.9975. Min Act: -0.1700

Data Index: 8136355 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.9908. Min Act: -0.1700

Data Index: 6148233 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0273. Min Act: -0.1700

Data Index: 3248994 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0255. Min Act: -0.1700

Data Index: 3716097 (Open Web Text)

Max Activating Token Index: 167

Text #16

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0065. Min Act: -0.1700

Data Index: 1695735 (Open Web Text)

Max Activating Token Index: 557

Text #17

Max Range: 3.3951. Min Range: -3.3951

Max Act: 3.0126. Min Act: -0.1700

Data Index: 5466460 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.9848. Min Act: -0.1700

Data Index: 3605190 (Open Web Text)

Max Activating Token Index: 891

Text #19

Max Range: 3.3951. Min Range: -3.3951

Max Act: 2.9708. Min Act: -0.1700

Data Index: 6177800 (Open Web Text)

Max Activating Token Index: 209