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

Dataset: Open Web Text

Neuron 1097 in Layer 2

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: 4.8798. Min Range: -4.8798

Max Act: 4.8798. Min Act: -0.1700

Data Index: 8254477 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.8270. Min Act: -0.1700

Data Index: 5849048 (Open Web Text)

Max Activating Token Index: 445

Text #2

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.8455. Min Act: -0.1700

Data Index: 2304888 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.8313. Min Act: -0.1700

Data Index: 4302004 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.8034. Min Act: -0.1700

Data Index: 6647598 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.8115. Min Act: -0.1700

Data Index: 8212194 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.8060. Min Act: -0.1700

Data Index: 1569602 (Open Web Text)

Max Activating Token Index: 892

Text #7

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.8096. Min Act: -0.1700

Data Index: 856422 (Open Web Text)

Max Activating Token Index: 567

Text #8

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7864. Min Act: -0.1700

Data Index: 5626142 (Open Web Text)

Max Activating Token Index: 64

Text #9

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7679. Min Act: -0.1700

Data Index: 3136884 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7638. Min Act: -0.1700

Data Index: 6548167 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7670. Min Act: -0.1700

Data Index: 2708999 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7842. Min Act: -0.1700

Data Index: 4077361 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7457. Min Act: -0.1700

Data Index: 6181897 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7375. Min Act: -0.1700

Data Index: 6380007 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7361. Min Act: -0.1700

Data Index: 1760765 (Open Web Text)

Max Activating Token Index: 188

Text #16

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7252. Min Act: -0.1700

Data Index: 2956341 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7598. Min Act: -0.1700

Data Index: 6548169 (Open Web Text)

Max Activating Token Index: 56

Text #18

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7201. Min Act: -0.1700

Data Index: 5065278 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 4.8798. Min Range: -4.8798

Max Act: 4.7632. Min Act: -0.1700

Data Index: 5228840 (Open Web Text)

Max Activating Token Index: 274