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

Dataset: Open Web Text

Neuron 1546 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: 3.5489. Min Range: -3.5489

Max Act: 3.5489. Min Act: -0.1700

Data Index: 1631494 (Open Web Text)

Max Activating Token Index: 884

Text #1

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.4343. Min Act: -0.1700

Data Index: 7232367 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.4075. Min Act: -0.1700

Data Index: 926206 (Open Web Text)

Max Activating Token Index: 644

Text #3

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.3719. Min Act: -0.1700

Data Index: 6787729 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.3499. Min Act: -0.1700

Data Index: 820607 (Open Web Text)

Max Activating Token Index: 939

Text #5

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.3300. Min Act: -0.1700

Data Index: 49668 (Open Web Text)

Max Activating Token Index: 498

Text #6

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.3021. Min Act: -0.1700

Data Index: 6319105 (Open Web Text)

Max Activating Token Index: 483

Text #7

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2414. Min Act: -0.1700

Data Index: 7957724 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2502. Min Act: -0.1700

Data Index: 6928242 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2541. Min Act: -0.1700

Data Index: 2552472 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2298. Min Act: -0.1700

Data Index: 6807328 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2344. Min Act: -0.1700

Data Index: 3076499 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2381. Min Act: -0.1700

Data Index: 8360179 (Open Web Text)

Max Activating Token Index: 356

Text #13

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2238. Min Act: -0.1700

Data Index: 8339508 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2166. Min Act: -0.1700

Data Index: 4499856 (Open Web Text)

Max Activating Token Index: 502

Text #15

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2091. Min Act: -0.1700

Data Index: 8760132 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2043. Min Act: -0.1700

Data Index: 1788397 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.2017. Min Act: -0.1700

Data Index: 3474605 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.1967. Min Act: -0.1700

Data Index: 2376303 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 3.5489. Min Range: -3.5489

Max Act: 3.1969. Min Act: -0.1700

Data Index: 5241340 (Open Web Text)

Max Activating Token Index: 535