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

Dataset: Open Web Text

Neuron 1237 in Layer 5

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: 4.7726. Min Range: -4.7726

Max Act: 4.7726. Min Act: -0.1700

Data Index: 2271312 (Open Web Text)

Max Activating Token Index: 410

Text #1

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.7101. Min Act: -0.1700

Data Index: 7522930 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.7172. Min Act: -0.1700

Data Index: 3378520 (Open Web Text)

Max Activating Token Index: 35

Text #3

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.6578. Min Act: -0.1700

Data Index: 3155095 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.6653. Min Act: -0.1700

Data Index: 2042870 (Open Web Text)

Max Activating Token Index: 170

Text #5

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.6240. Min Act: -0.1700

Data Index: 3240302 (Open Web Text)

Max Activating Token Index: 281

Text #6

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5899. Min Act: -0.1700

Data Index: 1280980 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.6044. Min Act: -0.1700

Data Index: 8177044 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.6154. Min Act: -0.1700

Data Index: 613865 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5692. Min Act: -0.1700

Data Index: 8229838 (Open Web Text)

Max Activating Token Index: 918

Text #10

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5627. Min Act: -0.1700

Data Index: 3932139 (Open Web Text)

Max Activating Token Index: 267

Text #11

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5528. Min Act: -0.1700

Data Index: 273622 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5522. Min Act: -0.1700

Data Index: 4387835 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5489. Min Act: -0.1700

Data Index: 1297216 (Open Web Text)

Max Activating Token Index: 77

Text #14

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5722. Min Act: -0.1700

Data Index: 2677089 (Open Web Text)

Max Activating Token Index: 261

Text #15

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5679. Min Act: -0.1700

Data Index: 5464464 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5545. Min Act: -0.1700

Data Index: 7204728 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5168. Min Act: -0.1700

Data Index: 4759828 (Open Web Text)

Max Activating Token Index: 623

Text #18

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5269. Min Act: -0.1700

Data Index: 3031494 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 4.7726. Min Range: -4.7726

Max Act: 4.5153. Min Act: -0.1700

Data Index: 5767729 (Open Web Text)

Max Activating Token Index: 324