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

Dataset: Open Web Text

Neuron 675 in Layer 1

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: 8.0275. Min Range: -8.0275

Max Act: 8.0275. Min Act: -0.1700

Data Index: 3286027 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9813. Min Act: -0.1700

Data Index: 5792572 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9980. Min Act: -0.1700

Data Index: 1916715 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9664. Min Act: -0.1700

Data Index: 3952647 (Open Web Text)

Max Activating Token Index: 623

Text #4

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9430. Min Act: -0.1700

Data Index: 2556918 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9186. Min Act: -0.1700

Data Index: 8589255 (Open Web Text)

Max Activating Token Index: 422

Text #6

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9449. Min Act: -0.1700

Data Index: 8209362 (Open Web Text)

Max Activating Token Index: 214

Text #7

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9149. Min Act: -0.1700

Data Index: 8185888 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9536. Min Act: -0.1700

Data Index: 1482183 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9579. Min Act: -0.1700

Data Index: 8158104 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9277. Min Act: -0.1700

Data Index: 7115257 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9327. Min Act: -0.1700

Data Index: 6018316 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.8859. Min Act: -0.1700

Data Index: 2004962 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.8601. Min Act: -0.1700

Data Index: 2033628 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.8856. Min Act: -0.1700

Data Index: 2139057 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9161. Min Act: -0.1700

Data Index: 2141931 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9301. Min Act: -0.1700

Data Index: 2403006 (Open Web Text)

Max Activating Token Index: 585

Text #17

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.8696. Min Act: -0.1700

Data Index: 2646797 (Open Web Text)

Max Activating Token Index: 156

Text #18

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.9107. Min Act: -0.1700

Data Index: 2748051 (Open Web Text)

Max Activating Token Index: 56

Text #19

Max Range: 8.0275. Min Range: -8.0275

Max Act: 7.8784. Min Act: -0.1700

Data Index: 485723 (Open Web Text)

Max Activating Token Index: 439