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

Dataset: Open Web Text

Neuron 2400 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: 4.9190. Min Range: -4.9190

Max Act: 4.9190. Min Act: -0.1700

Data Index: 992226 (Open Web Text)

Max Activating Token Index: 543

Text #1

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8869. Min Act: -0.1700

Data Index: 3314034 (Open Web Text)

Max Activating Token Index: 389

Text #2

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8123. Min Act: -0.1700

Data Index: 2403098 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.8135. Min Act: -0.1700

Data Index: 4552208 (Open Web Text)

Max Activating Token Index: 307

Text #4

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.7100. Min Act: -0.1700

Data Index: 125366 (Open Web Text)

Max Activating Token Index: 240

Text #5

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.6379. Min Act: -0.1700

Data Index: 4552205 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.5724. Min Act: -0.1700

Data Index: 4599385 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.6431. Min Act: -0.1700

Data Index: 125363 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.5975. Min Act: -0.1700

Data Index: 5122952 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.6109. Min Act: -0.1700

Data Index: 5957034 (Open Web Text)

Max Activating Token Index: 752

Text #10

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.6085. Min Act: -0.1700

Data Index: 1074013 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.4679. Min Act: -0.1700

Data Index: 1074015 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.3902. Min Act: -0.1700

Data Index: 5003178 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.4125. Min Act: -0.1700

Data Index: 6405273 (Open Web Text)

Max Activating Token Index: 134

Text #14

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.3698. Min Act: -0.1700

Data Index: 1663179 (Open Web Text)

Max Activating Token Index: 958

Text #15

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.3639. Min Act: -0.1700

Data Index: 522518 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.4262. Min Act: -0.1700

Data Index: 4552206 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.3851. Min Act: -0.1700

Data Index: 1074017 (Open Web Text)

Max Activating Token Index: 57

Text #18

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.3790. Min Act: -0.1700

Data Index: 1606898 (Open Web Text)

Max Activating Token Index: 236

Text #19

Max Range: 4.9190. Min Range: -4.9190

Max Act: 4.3279. Min Act: -0.1700

Data Index: 3189721 (Open Web Text)

Max Activating Token Index: 14