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

Dataset: Open Web Text

Neuron 3059 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: 4.5147. Min Range: -4.5147

Max Act: 4.5147. Min Act: -0.1700

Data Index: 3725924 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4765. Min Act: -0.1700

Data Index: 2423965 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4484. Min Act: -0.1700

Data Index: 7026071 (Open Web Text)

Max Activating Token Index: 969

Text #3

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4672. Min Act: -0.1698

Data Index: 2189888 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4451. Min Act: -0.1700

Data Index: 3414219 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4312. Min Act: -0.1700

Data Index: 5887157 (Open Web Text)

Max Activating Token Index: 557

Text #6

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4372. Min Act: -0.1700

Data Index: 8568001 (Open Web Text)

Max Activating Token Index: 103

Text #7

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4727. Min Act: -0.1700

Data Index: 8505146 (Open Web Text)

Max Activating Token Index: 77

Text #8

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4728. Min Act: -0.1700

Data Index: 4745182 (Open Web Text)

Max Activating Token Index: 265

Text #9

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4494. Min Act: -0.1700

Data Index: 4537820 (Open Web Text)

Max Activating Token Index: 167

Text #10

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4613. Min Act: -0.1700

Data Index: 1763574 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4818. Min Act: -0.1700

Data Index: 7184177 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4435. Min Act: -0.1700

Data Index: 1289280 (Open Web Text)

Max Activating Token Index: 146

Text #13

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4420. Min Act: -0.1700

Data Index: 2110505 (Open Web Text)

Max Activating Token Index: 441

Text #14

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4207. Min Act: -0.1700

Data Index: 4250853 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4382. Min Act: -0.1700

Data Index: 5224198 (Open Web Text)

Max Activating Token Index: 299

Text #16

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4733. Min Act: -0.1700

Data Index: 5417693 (Open Web Text)

Max Activating Token Index: 921

Text #17

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.3768. Min Act: -0.1700

Data Index: 5742399 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.4322. Min Act: -0.1700

Data Index: 3990783 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 4.5147. Min Range: -4.5147

Max Act: 4.3354. Min Act: -0.1700

Data Index: 5878620 (Open Web Text)

Max Activating Token Index: 273