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

Dataset: Open Web Text

Neuron 106 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: 3.4540. Min Range: -3.4540

Max Act: 3.4540. Min Act: -0.1700

Data Index: 8137552 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3939. Min Act: -0.1700

Data Index: 7677996 (Open Web Text)

Max Activating Token Index: 87

Text #2

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3377. Min Act: -0.1700

Data Index: 7907556 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2999. Min Act: -0.1700

Data Index: 1325212 (Open Web Text)

Max Activating Token Index: 654

Text #4

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.3028. Min Act: -0.1700

Data Index: 6876611 (Open Web Text)

Max Activating Token Index: 377

Text #5

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2917. Min Act: -0.1700

Data Index: 2434354 (Open Web Text)

Max Activating Token Index: 310

Text #6

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2499. Min Act: -0.1700

Data Index: 3717576 (Open Web Text)

Max Activating Token Index: 516

Text #7

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2641. Min Act: -0.1700

Data Index: 4568892 (Open Web Text)

Max Activating Token Index: 238

Text #8

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2636. Min Act: -0.1700

Data Index: 2398850 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2645. Min Act: -0.1700

Data Index: 1031245 (Open Web Text)

Max Activating Token Index: 643

Text #10

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2407. Min Act: -0.1700

Data Index: 8742447 (Open Web Text)

Max Activating Token Index: 153

Text #11

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2523. Min Act: -0.1700

Data Index: 7438619 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2499. Min Act: -0.1700

Data Index: 7485855 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2449. Min Act: -0.1700

Data Index: 1204137 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2110. Min Act: -0.1700

Data Index: 2384220 (Open Web Text)

Max Activating Token Index: 162

Text #15

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2136. Min Act: -0.1700

Data Index: 7562773 (Open Web Text)

Max Activating Token Index: 566

Text #16

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2235. Min Act: -0.1700

Data Index: 4591123 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2176. Min Act: -0.1700

Data Index: 4771660 (Open Web Text)

Max Activating Token Index: 807

Text #18

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.2292. Min Act: -0.1700

Data Index: 5814623 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 3.4540. Min Range: -3.4540

Max Act: 3.1897. Min Act: -0.1700

Data Index: 4069730 (Open Web Text)

Max Activating Token Index: 475