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

Dataset: Open Web Text

Neuron 848 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: 4.0883. Min Range: -4.0883

Max Act: 4.0883. Min Act: -0.1700

Data Index: 2231786 (Open Web Text)

Max Activating Token Index: 911

Text #1

Max Range: 4.0883. Min Range: -4.0883

Max Act: 4.0300. Min Act: -0.1700

Data Index: 5983727 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.9136. Min Act: -0.1700

Data Index: 3441497 (Open Web Text)

Max Activating Token Index: 302

Text #3

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.9107. Min Act: -0.1700

Data Index: 4350119 (Open Web Text)

Max Activating Token Index: 878

Text #4

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8921. Min Act: -0.1700

Data Index: 2406282 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8428. Min Act: -0.1700

Data Index: 1033196 (Open Web Text)

Max Activating Token Index: 50

Text #6

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8694. Min Act: -0.1700

Data Index: 3354288 (Open Web Text)

Max Activating Token Index: 299

Text #7

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8455. Min Act: -0.1700

Data Index: 4809692 (Open Web Text)

Max Activating Token Index: 822

Text #8

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8342. Min Act: -0.1700

Data Index: 1752429 (Open Web Text)

Max Activating Token Index: 972

Text #9

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8266. Min Act: -0.1700

Data Index: 5783760 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8268. Min Act: -0.1700

Data Index: 6546182 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8413. Min Act: -0.1700

Data Index: 1914774 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8110. Min Act: -0.1700

Data Index: 5848539 (Open Web Text)

Max Activating Token Index: 845

Text #13

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8295. Min Act: -0.1700

Data Index: 8585290 (Open Web Text)

Max Activating Token Index: 817

Text #14

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8338. Min Act: -0.1700

Data Index: 7463184 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8440. Min Act: -0.1700

Data Index: 3538429 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8173. Min Act: -0.1700

Data Index: 2937956 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8140. Min Act: -0.1700

Data Index: 5783768 (Open Web Text)

Max Activating Token Index: 965

Text #18

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.7803. Min Act: -0.1700

Data Index: 112053 (Open Web Text)

Max Activating Token Index: 267

Text #19

Max Range: 4.0883. Min Range: -4.0883

Max Act: 3.8098. Min Act: -0.1700

Data Index: 1713212 (Open Web Text)

Max Activating Token Index: 5