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

Dataset: Open Web Text

Neuron 2993 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: 2.3213. Min Range: -2.3213

Max Act: 2.3207. Min Act: -0.1700

Data Index: 6955538 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.3213. Min Act: -0.1700

Data Index: 889457 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.3136. Min Act: -0.1700

Data Index: 7965222 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2776. Min Act: -0.1700

Data Index: 3423139 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2861. Min Act: -0.1700

Data Index: 3958613 (Open Web Text)

Max Activating Token Index: 204

Text #5

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2594. Min Act: -0.1700

Data Index: 3831635 (Open Web Text)

Max Activating Token Index: 841

Text #6

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2731. Min Act: -0.1700

Data Index: 5812418 (Open Web Text)

Max Activating Token Index: 453

Text #7

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2566. Min Act: -0.1700

Data Index: 1029766 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2419. Min Act: -0.1700

Data Index: 6518894 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2449. Min Act: -0.1700

Data Index: 8236963 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2419. Min Act: -0.1700

Data Index: 4737834 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2518. Min Act: -0.1700

Data Index: 3482925 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2380. Min Act: -0.1700

Data Index: 7875090 (Open Web Text)

Max Activating Token Index: 702

Text #13

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2338. Min Act: -0.1700

Data Index: 989945 (Open Web Text)

Max Activating Token Index: 645

Text #14

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2475. Min Act: -0.1700

Data Index: 8464891 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2449. Min Act: -0.1700

Data Index: 7501931 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2281. Min Act: -0.1700

Data Index: 1736591 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2304. Min Act: -0.1700

Data Index: 4447759 (Open Web Text)

Max Activating Token Index: 263

Text #18

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2095. Min Act: -0.1700

Data Index: 7836468 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 2.3213. Min Range: -2.3213

Max Act: 2.2125. Min Act: -0.1700

Data Index: 6305931 (Open Web Text)

Max Activating Token Index: 525