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

Dataset: Open Web Text

Neuron 1177 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: 1.9049. Min Range: -1.9049

Max Act: 1.8931. Min Act: -0.1700

Data Index: 1956813 (Open Web Text)

Max Activating Token Index: 976

Text #1

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.9049. Min Act: -0.1700

Data Index: 6220063 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8815. Min Act: -0.1700

Data Index: 7591620 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8649. Min Act: -0.1700

Data Index: 6910188 (Open Web Text)

Max Activating Token Index: 428

Text #4

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8799. Min Act: -0.1700

Data Index: 7695685 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8585. Min Act: -0.1700

Data Index: 2599565 (Open Web Text)

Max Activating Token Index: 345

Text #6

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8397. Min Act: -0.1700

Data Index: 3168312 (Open Web Text)

Max Activating Token Index: 484

Text #7

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8369. Min Act: -0.1700

Data Index: 2354580 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8329. Min Act: -0.1700

Data Index: 7695687 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8179. Min Act: -0.1700

Data Index: 2576842 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8148. Min Act: -0.1700

Data Index: 7003304 (Open Web Text)

Max Activating Token Index: 658

Text #11

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8095. Min Act: -0.1700

Data Index: 2051318 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.7811. Min Act: -0.1700

Data Index: 6362680 (Open Web Text)

Max Activating Token Index: 403

Text #13

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8168. Min Act: -0.1700

Data Index: 6028244 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8049. Min Act: -0.1700

Data Index: 3736434 (Open Web Text)

Max Activating Token Index: 946

Text #15

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8035. Min Act: -0.1700

Data Index: 3334908 (Open Web Text)

Max Activating Token Index: 352

Text #16

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.8114. Min Act: -0.1700

Data Index: 3298669 (Open Web Text)

Max Activating Token Index: 474

Text #17

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.7789. Min Act: -0.1700

Data Index: 5817307 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.7823. Min Act: -0.1700

Data Index: 3417630 (Open Web Text)

Max Activating Token Index: 950

Text #19

Max Range: 1.9049. Min Range: -1.9049

Max Act: 1.7786. Min Act: -0.1700

Data Index: 6359989 (Open Web Text)

Max Activating Token Index: 629