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

Dataset: Open Web Text

Neuron 84 in Layer 2

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: 4.1712. Min Range: -4.1712

Max Act: 4.1712. Min Act: -0.1700

Data Index: 5735995 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 4.1712. Min Range: -4.1712

Max Act: 4.0333. Min Act: -0.1700

Data Index: 6246889 (Open Web Text)

Max Activating Token Index: 947

Text #2

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.9781. Min Act: -0.1700

Data Index: 2219538 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.9163. Min Act: -0.1700

Data Index: 8771857 (Open Web Text)

Max Activating Token Index: 321

Text #4

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.8698. Min Act: -0.1700

Data Index: 1566551 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.8002. Min Act: -0.1700

Data Index: 5047806 (Open Web Text)

Max Activating Token Index: 176

Text #6

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7559. Min Act: -0.1700

Data Index: 1950755 (Open Web Text)

Max Activating Token Index: 892

Text #7

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7596. Min Act: -0.1700

Data Index: 4241999 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7780. Min Act: -0.1700

Data Index: 5121944 (Open Web Text)

Max Activating Token Index: 100

Text #9

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7440. Min Act: -0.1700

Data Index: 6409913 (Open Web Text)

Max Activating Token Index: 265

Text #10

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7248. Min Act: -0.1700

Data Index: 4883057 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.7182. Min Act: -0.1700

Data Index: 144722 (Open Web Text)

Max Activating Token Index: 341

Text #12

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6889. Min Act: -0.1700

Data Index: 3134421 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6787. Min Act: -0.1700

Data Index: 7656635 (Open Web Text)

Max Activating Token Index: 222

Text #14

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6970. Min Act: -0.1700

Data Index: 7505745 (Open Web Text)

Max Activating Token Index: 342

Text #15

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6517. Min Act: -0.1700

Data Index: 7486198 (Open Web Text)

Max Activating Token Index: 36

Text #16

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6524. Min Act: -0.1700

Data Index: 2446472 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6421. Min Act: -0.1700

Data Index: 5802790 (Open Web Text)

Max Activating Token Index: 798

Text #18

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.6100. Min Act: -0.1700

Data Index: 6511606 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 4.1712. Min Range: -4.1712

Max Act: 3.5960. Min Act: -0.1700

Data Index: 2150943 (Open Web Text)

Max Activating Token Index: 20