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

Dataset: Open Web Text

Neuron 315 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: 4.3691. Min Range: -4.3691

Max Act: 4.3691. Min Act: -0.1700

Data Index: 3742699 (Open Web Text)

Max Activating Token Index: 75

Text #1

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.3372. Min Act: -0.1700

Data Index: 4861265 (Open Web Text)

Max Activating Token Index: 247

Text #2

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.2220. Min Act: -0.1700

Data Index: 6781953 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.2189. Min Act: -0.1700

Data Index: 4233329 (Open Web Text)

Max Activating Token Index: 243

Text #4

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1489. Min Act: -0.1700

Data Index: 3623800 (Open Web Text)

Max Activating Token Index: 264

Text #5

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1700. Min Act: -0.1700

Data Index: 7721166 (Open Web Text)

Max Activating Token Index: 53

Text #6

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1547. Min Act: -0.1700

Data Index: 4047155 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1380. Min Act: -0.1700

Data Index: 4218535 (Open Web Text)

Max Activating Token Index: 82

Text #8

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1675. Min Act: -0.1700

Data Index: 7578985 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1668. Min Act: -0.1700

Data Index: 5777042 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1642. Min Act: -0.1700

Data Index: 2008251 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1357. Min Act: -0.1700

Data Index: 1432758 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1334. Min Act: -0.1700

Data Index: 2695730 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1342. Min Act: -0.1700

Data Index: 1918716 (Open Web Text)

Max Activating Token Index: 623

Text #14

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1238. Min Act: -0.1700

Data Index: 6261908 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1194. Min Act: -0.1700

Data Index: 1020343 (Open Web Text)

Max Activating Token Index: 293

Text #16

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1259. Min Act: -0.1700

Data Index: 272863 (Open Web Text)

Max Activating Token Index: 338

Text #17

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1156. Min Act: -0.1700

Data Index: 2825151 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1226. Min Act: -0.1700

Data Index: 2008015 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 4.3691. Min Range: -4.3691

Max Act: 4.1438. Min Act: -0.1700

Data Index: 6453204 (Open Web Text)

Max Activating Token Index: 225