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

Dataset: Open Web Text

Neuron 2215 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: 3.9432. Min Range: -3.9432

Max Act: 3.9432. Min Act: -0.1700

Data Index: 1212353 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8867. Min Act: -0.1700

Data Index: 782661 (Open Web Text)

Max Activating Token Index: 335

Text #2

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8507. Min Act: -0.1700

Data Index: 3438303 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8710. Min Act: -0.1700

Data Index: 5390878 (Open Web Text)

Max Activating Token Index: 931

Text #4

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8548. Min Act: -0.1700

Data Index: 3438302 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8415. Min Act: -0.1700

Data Index: 5874591 (Open Web Text)

Max Activating Token Index: 745

Text #6

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8183. Min Act: -0.1700

Data Index: 6606445 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8304. Min Act: -0.1700

Data Index: 6028689 (Open Web Text)

Max Activating Token Index: 895

Text #8

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7986. Min Act: -0.1700

Data Index: 1138226 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7955. Min Act: -0.1700

Data Index: 5692658 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8060. Min Act: -0.1700

Data Index: 3949815 (Open Web Text)

Max Activating Token Index: 321

Text #11

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7907. Min Act: -0.1700

Data Index: 5084178 (Open Web Text)

Max Activating Token Index: 134

Text #12

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7967. Min Act: -0.1700

Data Index: 7315469 (Open Web Text)

Max Activating Token Index: 274

Text #13

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8064. Min Act: -0.1700

Data Index: 3438305 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7739. Min Act: -0.1700

Data Index: 5527057 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7748. Min Act: -0.1700

Data Index: 4066503 (Open Web Text)

Max Activating Token Index: 590

Text #16

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7804. Min Act: -0.1700

Data Index: 3678687 (Open Web Text)

Max Activating Token Index: 68

Text #17

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7604. Min Act: -0.1700

Data Index: 2511430 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7994. Min Act: -0.1700

Data Index: 2301057 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8017. Min Act: -0.1700

Data Index: 6236935 (Open Web Text)

Max Activating Token Index: 814