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

Dataset: Open Web Text

Neuron 2117 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: 3.3698. Min Range: -3.3698

Max Act: 3.3659. Min Act: -0.1700

Data Index: 4034257 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.3698. Min Act: -0.1700

Data Index: 102220 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2578. Min Act: -0.1700

Data Index: 1015496 (Open Web Text)

Max Activating Token Index: 889

Text #3

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.3127. Min Act: -0.1700

Data Index: 2023871 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.3000. Min Act: -0.1700

Data Index: 4333316 (Open Web Text)

Max Activating Token Index: 912

Text #5

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.3093. Min Act: -0.1700

Data Index: 164147 (Open Web Text)

Max Activating Token Index: 121

Text #6

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.3138. Min Act: -0.1700

Data Index: 1774799 (Open Web Text)

Max Activating Token Index: 421

Text #7

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2997. Min Act: -0.1700

Data Index: 6519260 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2368. Min Act: -0.1700

Data Index: 1945210 (Open Web Text)

Max Activating Token Index: 159

Text #9

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2477. Min Act: -0.1700

Data Index: 3969726 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2556. Min Act: -0.1700

Data Index: 4128865 (Open Web Text)

Max Activating Token Index: 970

Text #11

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2449. Min Act: -0.1700

Data Index: 3647697 (Open Web Text)

Max Activating Token Index: 732

Text #12

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2484. Min Act: -0.1700

Data Index: 4530493 (Open Web Text)

Max Activating Token Index: 572

Text #13

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2335. Min Act: -0.1700

Data Index: 4034259 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2206. Min Act: -0.1700

Data Index: 8108035 (Open Web Text)

Max Activating Token Index: 1008

Text #15

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2217. Min Act: -0.1700

Data Index: 4034256 (Open Web Text)

Max Activating Token Index: 74

Text #16

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2334. Min Act: -0.1700

Data Index: 7186996 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2165. Min Act: -0.1700

Data Index: 1421963 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2119. Min Act: -0.1700

Data Index: 470633 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 3.3698. Min Range: -3.3698

Max Act: 3.2138. Min Act: -0.1700

Data Index: 4566788 (Open Web Text)

Max Activating Token Index: 22