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

Dataset: Open Web Text

Neuron 278 in Layer 4

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: 3.7323. Min Range: -3.7323

Max Act: 3.7323. Min Act: -0.1700

Data Index: 2124110 (Open Web Text)

Max Activating Token Index: 108

Text #1

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.6523. Min Act: -0.1700

Data Index: 33762 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.6067. Min Act: -0.1700

Data Index: 4475193 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5831. Min Act: -0.1700

Data Index: 779135 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5503. Min Act: -0.1700

Data Index: 5261234 (Open Web Text)

Max Activating Token Index: 214

Text #5

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5876. Min Act: -0.1700

Data Index: 5738157 (Open Web Text)

Max Activating Token Index: 832

Text #6

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5537. Min Act: -0.1700

Data Index: 5388311 (Open Web Text)

Max Activating Token Index: 127

Text #7

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5197. Min Act: -0.1700

Data Index: 5406010 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5407. Min Act: -0.1700

Data Index: 6320536 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1178907 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5103. Min Act: -0.1700

Data Index: 6875321 (Open Web Text)

Max Activating Token Index: 118

Text #11

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5111. Min Act: -0.1700

Data Index: 4388073 (Open Web Text)

Max Activating Token Index: 199

Text #12

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.4988. Min Act: -0.1700

Data Index: 6195882 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5180. Min Act: -0.1700

Data Index: 7613682 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.4950. Min Act: -0.1700

Data Index: 4681383 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.5001. Min Act: -0.1700

Data Index: 4171146 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.4851. Min Act: -0.1700

Data Index: 6381454 (Open Web Text)

Max Activating Token Index: 104

Text #17

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.4866. Min Act: -0.1700

Data Index: 1176391 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.4705. Min Act: -0.1700

Data Index: 4306529 (Open Web Text)

Max Activating Token Index: 427

Text #19

Max Range: 3.7323. Min Range: -3.7323

Max Act: 3.4868. Min Act: -0.1700

Data Index: 494212 (Open Web Text)

Max Activating Token Index: 331