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

Dataset: Open Web Text

Neuron 1160 in Layer 6

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: 5.8225. Min Range: -5.8225

Max Act: 5.8188. Min Act: -0.1700

Data Index: 2366180 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.8225. Min Act: -0.1700

Data Index: 700637 (Open Web Text)

Max Activating Token Index: 221

Text #2

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.4394. Min Act: -0.1700

Data Index: 2684631 (Open Web Text)

Max Activating Token Index: 807

Text #3

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.3982. Min Act: -0.1700

Data Index: 3893188 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.3119. Min Act: -0.1700

Data Index: 6051334 (Open Web Text)

Max Activating Token Index: 189

Text #5

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.2709. Min Act: -0.1700

Data Index: 2590388 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.2109. Min Act: -0.1700

Data Index: 3957677 (Open Web Text)

Max Activating Token Index: 733

Text #7

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1682. Min Act: -0.1700

Data Index: 7652296 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.2194. Min Act: -0.1700

Data Index: 4281996 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1837. Min Act: -0.1700

Data Index: 7035604 (Open Web Text)

Max Activating Token Index: 177

Text #10

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1569. Min Act: -0.1700

Data Index: 8250093 (Open Web Text)

Max Activating Token Index: 717

Text #11

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1186. Min Act: -0.1700

Data Index: 5683199 (Open Web Text)

Max Activating Token Index: 333

Text #12

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1244. Min Act: -0.1700

Data Index: 7813539 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1737. Min Act: -0.1700

Data Index: 2490320 (Open Web Text)

Max Activating Token Index: 428

Text #14

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.0860. Min Act: -0.1700

Data Index: 8428469 (Open Web Text)

Max Activating Token Index: 529

Text #15

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1118. Min Act: -0.1700

Data Index: 1363755 (Open Web Text)

Max Activating Token Index: 237

Text #16

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1136. Min Act: -0.1700

Data Index: 3977626 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1089. Min Act: -0.1700

Data Index: 2511654 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.1286. Min Act: -0.1700

Data Index: 4867922 (Open Web Text)

Max Activating Token Index: 466

Text #19

Max Range: 5.8225. Min Range: -5.8225

Max Act: 5.0882. Min Act: -0.1700

Data Index: 1493599 (Open Web Text)

Max Activating Token Index: 558