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

Dataset: Open Web Text

Neuron 1880 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: 3.4359. Min Range: -3.4359

Max Act: 3.4264. Min Act: -0.1700

Data Index: 7811803 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.4306. Min Act: -0.1700

Data Index: 1964327 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.4359. Min Act: -0.1700

Data Index: 7657069 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.4135. Min Act: -0.1700

Data Index: 5069599 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3990. Min Act: -0.1700

Data Index: 6394081 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3997. Min Act: -0.1700

Data Index: 4021290 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.4085. Min Act: -0.1700

Data Index: 4589413 (Open Web Text)

Max Activating Token Index: 440

Text #7

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3695. Min Act: -0.1700

Data Index: 6601282 (Open Web Text)

Max Activating Token Index: 592

Text #8

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3753. Min Act: -0.1700

Data Index: 6438237 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3615. Min Act: -0.1700

Data Index: 2368053 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3897. Min Act: -0.1700

Data Index: 5105589 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3717. Min Act: -0.1700

Data Index: 2698084 (Open Web Text)

Max Activating Token Index: 73

Text #12

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3552. Min Act: -0.1700

Data Index: 3541684 (Open Web Text)

Max Activating Token Index: 547

Text #13

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3645. Min Act: -0.1700

Data Index: 65083 (Open Web Text)

Max Activating Token Index: 431

Text #14

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3694. Min Act: -0.1700

Data Index: 2489707 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3719. Min Act: -0.1700

Data Index: 3999121 (Open Web Text)

Max Activating Token Index: 916

Text #16

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3142. Min Act: -0.1700

Data Index: 3715581 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3180. Min Act: -0.1700

Data Index: 5679131 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3217. Min Act: -0.1700

Data Index: 65081 (Open Web Text)

Max Activating Token Index: 365

Text #19

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3271. Min Act: -0.1700

Data Index: 8680995 (Open Web Text)

Max Activating Token Index: 270