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

Dataset: Open Web Text

Neuron 323 in Layer 0

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: 7.6191. Min Range: -7.6191

Max Act: 7.6191. Min Act: -0.1700

Data Index: 2173946 (Open Web Text)

Max Activating Token Index: 390

Text #1

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.4082. Min Act: -0.1700

Data Index: 1670284 (Open Web Text)

Max Activating Token Index: 797

Text #2

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.3387. Min Act: -0.1700

Data Index: 3291367 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.3158. Min Act: -0.1700

Data Index: 1003843 (Open Web Text)

Max Activating Token Index: 966

Text #4

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.3042. Min Act: -0.1700

Data Index: 1003845 (Open Web Text)

Max Activating Token Index: 342

Text #5

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.2632. Min Act: -0.1700

Data Index: 1003844 (Open Web Text)

Max Activating Token Index: 956

Text #6

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.2142. Min Act: -0.1700

Data Index: 2459333 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.0964. Min Act: -0.1700

Data Index: 4570418 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.9828. Min Act: -0.1700

Data Index: 3565126 (Open Web Text)

Max Activating Token Index: 873

Text #9

Max Range: 7.6191. Min Range: -7.6191

Max Act: 7.0036. Min Act: -0.1700

Data Index: 3510846 (Open Web Text)

Max Activating Token Index: 834

Text #10

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.9799. Min Act: -0.1700

Data Index: 539068 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.8545. Min Act: -0.1700

Data Index: 7400867 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.8255. Min Act: -0.1700

Data Index: 1642458 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.8339. Min Act: -0.1688

Data Index: 4023818 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.8097. Min Act: -0.1700

Data Index: 2173947 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.7617. Min Act: -0.1700

Data Index: 4023819 (Open Web Text)

Max Activating Token Index: 419

Text #16

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.6485. Min Act: -0.1700

Data Index: 6399026 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.6387. Min Act: -0.1697

Data Index: 4023822 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.5319. Min Act: -0.1700

Data Index: 1388732 (Open Web Text)

Max Activating Token Index: 210

Text #19

Max Range: 7.6191. Min Range: -7.6191

Max Act: 6.4920. Min Act: -0.1688

Data Index: 4023794 (Open Web Text)

Max Activating Token Index: 420