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

Dataset: Open Web Text

Neuron 8 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: 3.0818. Min Range: -3.0818

Max Act: 3.0818. Min Act: -0.1700

Data Index: 2976268 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0586. Min Act: -0.1700

Data Index: 4914918 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0374. Min Act: -0.1700

Data Index: 5022173 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0542. Min Act: -0.1700

Data Index: 8468077 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0481. Min Act: -0.1700

Data Index: 4688936 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0187. Min Act: -0.1700

Data Index: 4023570 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0295. Min Act: -0.1700

Data Index: 3187745 (Open Web Text)

Max Activating Token Index: 134

Text #7

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0163. Min Act: -0.1700

Data Index: 6861285 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0183. Min Act: -0.1700

Data Index: 5386503 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0156. Min Act: -0.1700

Data Index: 4274585 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0006. Min Act: -0.1700

Data Index: 5802686 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 3.0818. Min Range: -3.0818

Max Act: 3.0003. Min Act: -0.1700

Data Index: 7570067 (Open Web Text)

Max Activating Token Index: 816

Text #12

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9876. Min Act: -0.1700

Data Index: 8770617 (Open Web Text)

Max Activating Token Index: 167

Text #13

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9865. Min Act: -0.1700

Data Index: 3461240 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9794. Min Act: -0.1700

Data Index: 973561 (Open Web Text)

Max Activating Token Index: 176

Text #15

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9739. Min Act: -0.1700

Data Index: 4039552 (Open Web Text)

Max Activating Token Index: 61

Text #16

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9673. Min Act: -0.1700

Data Index: 5459167 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9592. Min Act: -0.1700

Data Index: 8371781 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9594. Min Act: -0.1700

Data Index: 8760244 (Open Web Text)

Max Activating Token Index: 315

Text #19

Max Range: 3.0818. Min Range: -3.0818

Max Act: 2.9664. Min Act: -0.1700

Data Index: 8450289 (Open Web Text)

Max Activating Token Index: 143