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

Dataset: Open Web Text

Neuron 51 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: 3.8953. Min Range: -3.8953

Max Act: 3.8953. Min Act: -0.1700

Data Index: 3382994 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.8441. Min Act: -0.1700

Data Index: 7762900 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7874. Min Act: -0.1700

Data Index: 7623969 (Open Web Text)

Max Activating Token Index: 289

Text #3

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7510. Min Act: -0.1700

Data Index: 4957582 (Open Web Text)

Max Activating Token Index: 651

Text #4

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7261. Min Act: -0.1700

Data Index: 3369964 (Open Web Text)

Max Activating Token Index: 642

Text #5

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7104. Min Act: -0.1700

Data Index: 916499 (Open Web Text)

Max Activating Token Index: 592

Text #6

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7314. Min Act: -0.1700

Data Index: 4180000 (Open Web Text)

Max Activating Token Index: 447

Text #7

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7363. Min Act: -0.1700

Data Index: 8575557 (Open Web Text)

Max Activating Token Index: 313

Text #8

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7382. Min Act: -0.1700

Data Index: 2042517 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7076. Min Act: -0.1700

Data Index: 7815217 (Open Web Text)

Max Activating Token Index: 681

Text #10

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7089. Min Act: -0.1700

Data Index: 6642329 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.6995. Min Act: -0.1700

Data Index: 5913121 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.6884. Min Act: -0.1700

Data Index: 5613957 (Open Web Text)

Max Activating Token Index: 120

Text #13

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7055. Min Act: -0.1700

Data Index: 7057419 (Open Web Text)

Max Activating Token Index: 613

Text #14

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7171. Min Act: -0.1700

Data Index: 3329357 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.6862. Min Act: -0.1700

Data Index: 1316256 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.6813. Min Act: -0.1700

Data Index: 6081465 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.6781. Min Act: -0.1700

Data Index: 6397345 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.7114. Min Act: -0.1700

Data Index: 6507983 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.8953. Min Range: -3.8953

Max Act: 3.6826. Min Act: -0.1700

Data Index: 4957580 (Open Web Text)

Max Activating Token Index: 337