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

Dataset: Open Web Text

Neuron 3055 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: 1.7189. Min Range: -1.7189

Max Act: 1.7189. Min Act: -0.1700

Data Index: 2795396 (Open Web Text)

Max Activating Token Index: 179

Text #1

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6577. Min Act: -0.1700

Data Index: 8443871 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6401. Min Act: -0.1700

Data Index: 1824915 (Open Web Text)

Max Activating Token Index: 238

Text #3

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6392. Min Act: -0.1700

Data Index: 8380565 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6322. Min Act: -0.1700

Data Index: 1376804 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6247. Min Act: -0.1700

Data Index: 4789807 (Open Web Text)

Max Activating Token Index: 207

Text #6

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6295. Min Act: -0.1700

Data Index: 7071671 (Open Web Text)

Max Activating Token Index: 792

Text #7

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6151. Min Act: -0.1700

Data Index: 5529820 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6069. Min Act: -0.1700

Data Index: 5453156 (Open Web Text)

Max Activating Token Index: 87

Text #9

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6177. Min Act: -0.1700

Data Index: 6078940 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6151. Min Act: -0.1696

Data Index: 5943529 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6015. Min Act: -0.1700

Data Index: 5853097 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6110. Min Act: -0.1700

Data Index: 360861 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6082. Min Act: -0.1700

Data Index: 6338796 (Open Web Text)

Max Activating Token Index: 345

Text #14

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6009. Min Act: -0.1700

Data Index: 7765973 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6019. Min Act: -0.1700

Data Index: 7641747 (Open Web Text)

Max Activating Token Index: 146

Text #16

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5903. Min Act: -0.1700

Data Index: 3403499 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5899. Min Act: -0.1700

Data Index: 4675154 (Open Web Text)

Max Activating Token Index: 803

Text #18

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.6035. Min Act: -0.1700

Data Index: 4667948 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 1.7189. Min Range: -1.7189

Max Act: 1.5911. Min Act: -0.1700

Data Index: 6956 (Open Web Text)

Max Activating Token Index: 246