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

Dataset: Open Web Text

Neuron 2081 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: 1.6204. Min Range: -1.6204

Max Act: 1.6204. Min Act: -0.1481

Data Index: 8610951 (Open Web Text)

Max Activating Token Index: 73

Text #1

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5883. Min Act: -0.1309

Data Index: 3716341 (Open Web Text)

Max Activating Token Index: 951

Text #2

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5862. Min Act: -0.1472

Data Index: 7678360 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5907. Min Act: -0.1633

Data Index: 3306493 (Open Web Text)

Max Activating Token Index: 772

Text #4

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5584. Min Act: -0.1700

Data Index: 3189596 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5461. Min Act: -0.1680

Data Index: 5631094 (Open Web Text)

Max Activating Token Index: 745

Text #6

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5517. Min Act: -0.1603

Data Index: 5476068 (Open Web Text)

Max Activating Token Index: 147

Text #7

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5529. Min Act: -0.1699

Data Index: 1948003 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5437. Min Act: -0.1324

Data Index: 171084 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5456. Min Act: -0.1632

Data Index: 691938 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5330. Min Act: -0.1288

Data Index: 171083 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5450. Min Act: -0.1696

Data Index: 7475871 (Open Web Text)

Max Activating Token Index: 386

Text #12

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5484. Min Act: -0.1663

Data Index: 6356218 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5419. Min Act: -0.1658

Data Index: 3348909 (Open Web Text)

Max Activating Token Index: 167

Text #14

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5346. Min Act: -0.1493

Data Index: 8686442 (Open Web Text)

Max Activating Token Index: 356

Text #15

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5320. Min Act: -0.1700

Data Index: 1611314 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5247. Min Act: -0.1460

Data Index: 7678361 (Open Web Text)

Max Activating Token Index: 275

Text #17

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5187. Min Act: -0.1700

Data Index: 5228864 (Open Web Text)

Max Activating Token Index: 260

Text #18

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5195. Min Act: -0.1523

Data Index: 8039223 (Open Web Text)

Max Activating Token Index: 196

Text #19

Max Range: 1.6204. Min Range: -1.6204

Max Act: 1.5203. Min Act: -0.1481

Data Index: 3086666 (Open Web Text)

Max Activating Token Index: 115