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

Dataset: Open Web Text

Neuron 1330 in Layer 4

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: 1.3375. Min Range: -1.3375

Max Act: 1.3375. Min Act: -0.1700

Data Index: 3216834 (Open Web Text)

Max Activating Token Index: 234

Text #1

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.2681. Min Act: -0.1700

Data Index: 4472686 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.2615. Min Act: -0.1700

Data Index: 8235062 (Open Web Text)

Max Activating Token Index: 155

Text #3

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.2377. Min Act: -0.1700

Data Index: 2825360 (Open Web Text)

Max Activating Token Index: 207

Text #4

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.2367. Min Act: -0.1700

Data Index: 7468423 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.2179. Min Act: -0.1700

Data Index: 5417386 (Open Web Text)

Max Activating Token Index: 185

Text #6

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1981. Min Act: -0.1700

Data Index: 5757101 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1965. Min Act: -0.1700

Data Index: 3388404 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.2044. Min Act: -0.1700

Data Index: 2552650 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.2052. Min Act: -0.1700

Data Index: 5715961 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1875. Min Act: -0.1700

Data Index: 3384671 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1974. Min Act: -0.1700

Data Index: 1719511 (Open Web Text)

Max Activating Token Index: 194

Text #12

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1848. Min Act: -0.1700

Data Index: 2277910 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1728. Min Act: -0.1700

Data Index: 2042295 (Open Web Text)

Max Activating Token Index: 341

Text #14

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1699. Min Act: -0.1700

Data Index: 6991063 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1763. Min Act: -0.1700

Data Index: 2423325 (Open Web Text)

Max Activating Token Index: 206

Text #16

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1800. Min Act: -0.1700

Data Index: 2985409 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1741. Min Act: -0.1700

Data Index: 2624950 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1678. Min Act: -0.1700

Data Index: 4623311 (Open Web Text)

Max Activating Token Index: 239

Text #19

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1662. Min Act: -0.1700

Data Index: 1076087 (Open Web Text)

Max Activating Token Index: 206